{"title":"Firefly AIBOX Embedded PC","description":"\u003ch2\u003eFirefly AIBOX Embedded PC\u003c\/h2\u003e\u003cp\u003eEdge AI boxes for local LLM and video analytics: AIBOX-3588, AIBOX-1684, AIBOX-OrinNano\/OrinNX, and industrial AI edge hosts.\u003c\/p\u003e","products":[{"product_id":"aibox-9075-industrial-edge-computer","title":"AIBOX-9075 Industrial Edge Computer","description":"\u003cp class=\"geo-summary\" style=\"font-size:1rem;line-height:1.65;margin:0 0 1.25rem;padding:0 0 1rem;border-bottom:1px solid #e5e7eb;color:#1f2937\"\u003e\u003cstrong\u003eAIBOX-9075 Industrial Edge Computer\u003c\/strong\u003e is a Firefly product sold by Ai-Paipai. Key specifications — Soc: Qualcomm IQ-9075 · Ram: 36GB LPDDR5 (ECC supported) · Storage: 128GB UFS2.2 · Wireless network: Wi-Fi \u0026amp; Bluetooth: Supports Wi-Fi 6 and Bluetooth 5.2… · Storage expansion: 1 × M.2 (PCIe 4.0 x4 NVMe 2280 SSD expandable; located…. Typical applications: edge AI inference, machine vision and industrial automation. Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.) is an authorized distributor providing local technical support, pre-installed SDK \/ OS images, OEM \/ ODM customization, and worldwide shipping.\u003c\/p\u003e\n\u003c!-- Firefly product tabs --\u003e\n\u003cdiv class=\"fx-tabs\" data-fx-tabs\u003e\n  \u003cdiv class=\"fx-tablist\" role=\"tablist\"\u003e\n    \u003cbutton class=\"fx-tab is-active\" role=\"tab\" data-fx-tab=\"0\"\u003eDescription\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"1\"\u003eWhat's Included\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"2\"\u003eSpecifications\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"3\"\u003eDocuments\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"4\"\u003eShipping Information\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"5\"\u003eWhy Buy From Ai-Paipai?\u003c\/button\u003e\n  \u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel is-active\" data-fx-panel=\"0\"\u003e\n\u003cdiv style=\"border:2px solid #2b6cb0;background:#f0f7ff;padding:14px 18px;margin:0 0 18px;border-radius:8px;\"\u003e\n\u003ch3 style=\"margin:0 0 6px;color:#2b6cb0;\"\u003e✅ Authorized Distributor — Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.)\u003c\/h3\u003e\n\u003cp style=\"margin:0;font-size:14px;\"\u003eThis product is supplied by an \u003cb\u003eauthorized distributor\u003c\/b\u003e of the original brand.\nWe provide \u003cb\u003elocal technical support, pre-installed SDK \/ mirror images, and OEM \/ ODM customization\u003c\/b\u003e, plus fast global shipping.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cp\u003ePowered by Qualcomm IQ-9075 processor, delivering up to 200 TOPS of peak AI computing power and achieving 12TPS large model inference, enabling on-device private deployment of large language models. Its octa-core CPU runs at up to 2.36GHz, well-suited for high‑load edge AI and multi‑task concurrency. It features built‑in security subsystem and four real‑time cores. Leveraging Qualcomm Linux software stack, it supports Ubuntu\/Yocto systems and mainstream AI inference frameworks. With an industrial wide‑temperature design, it comes standard with GMSL2, CAN‑FD, RS485, and opto‑isolated I\/O.\u003c\/p\u003e\n\u003ch2 style=\"font-size: 25px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eHigh-Performance AI Processor IQ-9075\u003c\/li\u003e\n\u003cli\u003eGPU\/VPU Graphics \u0026amp; Multimedia Processing\u003c\/li\u003e\n\u003cli\u003eUp to 36GB LPDDR5 Memory\u003c\/li\u003e\n\u003cli\u003eAll-Scenario Multi-Standard Network Connectivity\u003c\/li\u003e\n\u003cli\u003e8-Channel GMSL2 Vision Capture Interface\u003c\/li\u003e\n\u003cli\u003eSupport -40°C to 85°C Wide Temperature\u003c\/li\u003e\n\u003cli\u003eRich Industrial Expansion Interfaces\u003c\/li\u003e\n\u003cli\u003eFull-Stack Software Ecosystem Support\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 25px;\"\u003e\u003cstrong\u003eProduct Overview\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/1_05_9042c4d7-88f0-4001-94a4-77ac1481567b.jpg?v=1781659995\" alt=\"\"\u003e\u003c\/strong\u003e\u003c\/p\u003e\n\u003chr\u003e\n\u003ch2\u003e\n  \u003c\/h2\u003e\n\u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"1\"\u003e\n    \u003ch3\u003eShipping list\u003c\/h3\u003e\n    \u003cul\u003e\n      \u003cli\u003eMain unit × 1\u003c\/li\u003e\n      \u003cli\u003ePower adapter \/ cable (region plug on request) × 1\u003c\/li\u003e\n      \u003cli\u003eAccessories vary by configuration — contact us for the exact included list.\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"2\"\u003e\n    \u003cdiv class=\"fx-specs\"\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eSoc\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eQualcomm IQ-9075\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eCpu\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eQualcomm Kryo® Gen6 CPU: Octa-core 64-bit (8×Kryo Gold Prime), up to 2.36 GHz\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eGpu\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eAdreno 663 GPU supports safe GPGPU compute, up to 840MHz\n· Graphics APIs: Vulkan 1.2, OpenGL ES 3.2\n· Compute APIs: Vulkan 1.2, OpenCL 2.0 FP, Adreno NN Direct\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eRam\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e36GB LPDDR5 (ECC supported)\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eStorage\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e128GB UFS2.2\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eStorage expansion\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e1 × M.2 (PCIe 4.0 x4 NVMe 2280 SSD expandable; located inside the computer)\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003ePower consumption\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eNormal: 12W(12V\/1000mA), Max: 60W(12V\/5000mA), Min(Sleep): 1.08W(12V\/90mA)\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eOs\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eUbuntu, Yocto Linux Software Stack\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eSoftware support\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eSupports private deployment of ultra-large parameter models under the Transformer architecture, including the Deepseek-R1 series, Gemma series, Llama series, Qwen series, Phi series and other large language models.\nSupports private deployment of image generation models such as Stable Diffusion.\nSupports the QNN AI inference framework, as well as multiple deep learning frameworks including TensorFlow, TensorFlow Lite, PyTorch, ONNX, Keras and Caffe.\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eDimension\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e110.2mm × 102.25mm × 72.0mm (without mounting ears)\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eEnvironment\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eOperating Temperature: -40℃ ~ 85℃, Storage Temperature: -40℃ ~ 90℃, Storage Humidity: 10% ~ 90%RH (non-condensing)\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eWireless network\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eWi-Fi \u0026amp; Bluetooth: Supports Wi-Fi 6 and Bluetooth 5.2 (expandable via internal M.2 E-KEY) 4G\/5G: Expandable via internal Mini PCIe\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eEthernet\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e2 × 2.5G Ethernet (2.5Gbps\/RJ45)\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eButton\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e1 × Power Button, 1 × Burn Button\u003c\/div\u003e\n\u003c\/div\u003e\n    \u003c\/div\u003e\n  \u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"3\"\u003e\n        \u003cdiv class=\"fx-docs\"\u003e\n      \u003cdiv class=\"fx-doc\"\u003e\n\u003cspan\u003eProduct tutorials\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-doc\"\u003e\n\u003cspan\u003eProduct datasheet\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-doc\"\u003e\n\u003cspan\u003eSDK software and firmware files\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e\n\u003c\/div\u003e\n    \u003c\/div\u003e\n    \u003cp class=\"fx-note\"\u003eDocument links will be replaced with the official Firefly resource URLs on request.\u003c\/p\u003e\n  \u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"4\"\u003e\n        \u003cp\u003e\u003cb\u003eOur cooperating carriers:\u003c\/b\u003e FedEx, DHL, UPS, SF Express\u003c\/p\u003e\n    \u003ch3\u003eDelivery Area And Cost\u003c\/h3\u003e\n    \u003cdiv class=\"fx-scroll\"\u003e\n      \u003ctable class=\"fx-table\"\u003e\n        \u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eCountry\/Region\u003c\/th\u003e\n\u003cth\u003e0–2kg\u003c\/th\u003e\n\u003cth\u003e2–3kg\u003c\/th\u003e\n\u003cth\u003e3–4kg\u003c\/th\u003e\n\u003cth\u003e4–5kg\u003c\/th\u003e\n\u003cth\u003e5–6kg\u003c\/th\u003e\n\u003cth\u003e6–7kg\u003c\/th\u003e\n\u003cth\u003e7–8kg\u003c\/th\u003e\n\u003cth\u003e8–9kg\u003c\/th\u003e\n\u003cth\u003e9–10kg\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n        \u003ctbody\u003e\n          \u003ctr\u003e\n\u003ctd\u003eJapan, Taiwan, Hong Kong, Macau\u003c\/td\u003e\n\u003ctd\u003e$15\u003c\/td\u003e\n\u003ctd\u003e$20\u003c\/td\u003e\n\u003ctd\u003e$25\u003c\/td\u003e\n\u003ctd\u003e$30\u003c\/td\u003e\n\u003ctd\u003e$35\u003c\/td\u003e\n\u003ctd\u003e$40\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$50\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eSingapore, Thailand, Malaysia\u003c\/td\u003e\n\u003ctd\u003e$20\u003c\/td\u003e\n\u003ctd\u003e$25\u003c\/td\u003e\n\u003ctd\u003e$30\u003c\/td\u003e\n\u003ctd\u003e$35\u003c\/td\u003e\n\u003ctd\u003e$40\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$50\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003ctd\u003e$60\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eIndonesia, Philippines\u003c\/td\u003e\n\u003ctd\u003e$25\u003c\/td\u003e\n\u003ctd\u003e$30\u003c\/td\u003e\n\u003ctd\u003e$40\u003c\/td\u003e\n\u003ctd\u003e$50\u003c\/td\u003e\n\u003ctd\u003e$60\u003c\/td\u003e\n\u003ctd\u003e$70\u003c\/td\u003e\n\u003ctd\u003e$80\u003c\/td\u003e\n\u003ctd\u003e$85\u003c\/td\u003e\n\u003ctd\u003e$95\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eSouth Korea\u003c\/td\u003e\n\u003ctd\u003e$25\u003c\/td\u003e\n\u003ctd\u003e$35\u003c\/td\u003e\n\u003ctd\u003e$35\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003ctd\u003e$65\u003c\/td\u003e\n\u003ctd\u003e$65\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eUnited States, Australia, New Zealand, Canada, UK, and most of Western Europe\u003c\/td\u003e\n\u003ctd\u003e$30\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003ctd\u003e$65\u003c\/td\u003e\n\u003ctd\u003e$75\u003c\/td\u003e\n\u003ctd\u003e$85\u003c\/td\u003e\n\u003ctd\u003e$95\u003c\/td\u003e\n\u003ctd\u003e$105\u003c\/td\u003e\n\u003ctd\u003e$115\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eOther regions (Eastern Europe, Middle East, Latin America, etc.)\u003c\/td\u003e\n\u003ctd\u003e$50\u003c\/td\u003e\n\u003ctd\u003e$65\u003c\/td\u003e\n\u003ctd\u003e$80\u003c\/td\u003e\n\u003ctd\u003e$95\u003c\/td\u003e\n\u003ctd\u003e$110\u003c\/td\u003e\n\u003ctd\u003e$125\u003c\/td\u003e\n\u003ctd\u003e$135\u003c\/td\u003e\n\u003ctd\u003e$150\u003c\/td\u003e\n\u003ctd\u003e$165\u003c\/td\u003e\n\u003c\/tr\u003e\n        \u003c\/tbody\u003e\n      \u003c\/table\u003e\n    \u003c\/div\u003e\n    \u003cp class=\"fx-note\"\u003eShipping time is for reference only; the actual situation shall prevail.\u003c\/p\u003e\n  \u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"5\"\u003e\n    Why Buy From Ai-Paipai?\n\u003cul\u003e\n\u003cli\u003e\n\u003cb\u003eAuthorized \u0026amp; Genuine\u003c\/b\u003e — sourced directly from brand-approved channels.\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eLocal Engineering Support\u003c\/b\u003e — datasheets, SDKs, and pre-flashed images in English and Chinese.\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eOEM \/ ODM \u0026amp; FPGA Customization\u003c\/b\u003e — tailor specs, enclosures, and BSP for your project.\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eOne-Stop Sourcing\u003c\/b\u003e — Firefly + youyeetoo + our own FPGA \/ edge lineup in one store.\u003c\/li\u003e\n\u003c\/ul\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e\n\n\u003cstyle\u003e\n  .fx-tabs{margin:24px 0;border:1px solid #e5e7eb;border-radius:10px;overflow:hidden;background:#fff}\n  .fx-tablist{display:flex;flex-wrap:wrap;gap:0;border-bottom:1px solid #e5e7eb;background:#f8fafc}\n  .fx-tab{flex:1 1 auto;min-width:120px;padding:14px 16px;border:0;background:transparent;cursor:pointer;font:600 14px\/1.3 inherit;color:#475569;border-bottom:3px solid transparent;transition:.18s}\n  .fx-tab:hover{color:#0f172a;background:#eef2f7}\n  .fx-tab.is-active{color:#0f172a;border-bottom-color:#2563eb;background:#fff}\n  .fx-panel{display:none;padding:22px 24px}\n  .fx-panel.is-active{display:block}\n  .fx-panel h3{font-size:16px;margin:22px 0 8px;font-weight:700}\n  .fx-panel h3:first-child{margin-top:0}\n  .fx-panel p{margin:10px 0;line-height:1.65}\n  .fx-panel ul{margin:10px 0;padding-left:22px}\n  .fx-panel li{margin:6px 0;line-height:1.6}\n  .fx-auth{background:#f0fdf4;border:1px solid #bbf7d0;border-radius:8px;padding:12px 14px;margin:0 0 16px;font-size:14px;line-height:1.6}\n  .fx-specs{border-top:1px solid #eef2f7}\n  .fx-spec{display:grid;grid-template-columns:230px 1fr;gap:16px;padding:12px 4px;border-bottom:1px solid #eef2f7}\n  .fx-k{font-weight:700;color:#334155}\n  .fx-v{color:#475569}\n  .fx-docs{display:flex;flex-direction:column;gap:10px}\n  .fx-doc{display:flex;justify-content:space-between;align-items:center;gap:12px;padding:12px 14px;border:1px solid #e5e7eb;border-radius:8px}\n  .fx-doc a{color:#2563eb;font-weight:700;text-decoration:none}\n  .fx-doc a:hover{text-decoration:underline}\n  .fx-scroll{overflow-x:auto}\n  .fx-table{border-collapse:collapse;width:100%;min-width:760px;font-size:13px}\n  .fx-table th,.fx-table td{border:1px solid #e5e7eb;padding:8px 10px;text-align:left}\n  .fx-table th{background:#f8fafc;font-weight:700}\n  .fx-note{color:#64748b;font-size:13px;margin-top:12px}\n  @media (max-width:749px){.fx-spec{grid-template-columns:1fr;gap:4px}.fx-tab{min-width:50%;flex:1 1 50%}.fx-panel{padding:16px}}\n\u003c\/style\u003e\n\n\u003cscript\u003e\n  (function () {\n    var roots = document.querySelectorAll('[data-fx-tabs]');\n    roots.forEach(function (root) {\n      var tabs = root.querySelectorAll('[data-fx-tab]');\n      var panels = root.querySelectorAll('[data-fx-panel]');\n      tabs.forEach(function (t) {\n        t.addEventListener('click', function () {\n          var i = t.getAttribute('data-fx-tab');\n          tabs.forEach(function (x) { x.classList.toggle('is-active', x === t); });\n          panels.forEach(function (p) { p.classList.toggle('is-active', p.getAttribute('data-fx-panel') === i); });\n        });\n      });\n    });\n  })();\n\u003c\/script\u003e","brand":"Firefly","offers":[{"title":"36G","offer_id":48422465339650,"sku":"firefly-aibox-9075-industrial-edge-computer-47092801929300","price":1239.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0837\/5953\/0242\/files\/1_0e7d6f11-bf91-421a-8bd6-fb1852c4d807.webp?v=1788244273"},{"product_id":"aibox-pro-edge-computing-computer","title":"AIBOX PRO Edge Computing Computer","description":"\u003cp class=\"geo-summary\" style=\"font-size:1rem;line-height:1.65;margin:0 0 1.25rem;padding:0 0 1rem;border-bottom:1px solid #e5e7eb;color:#1f2937\"\u003e\u003cstrong\u003eAIBOX PRO Edge Computing Computer\u003c\/strong\u003e is a Firefly product sold by Ai-Paipai. We provide local technical support, pre-installed SDK \/ mirror images, and OEM \/ ODM customization , plus fast global shipping. AIBOX PRO is a compact host designed for edge large model deployment. Typical applications: edge AI inference. Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.) is an authorized distributor providing local technical support, pre-installed SDK \/ OS images, OEM \/ ODM customization, and worldwide shipping.\u003c\/p\u003e\n\u003c!-- Firefly product tabs --\u003e\n\u003cdiv class=\"fx-tabs\" data-fx-tabs\u003e\n  \u003cdiv class=\"fx-tablist\" role=\"tablist\"\u003e\n    \u003cbutton class=\"fx-tab is-active\" role=\"tab\" data-fx-tab=\"0\"\u003eDescription\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"1\"\u003eWhat's Included\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"2\"\u003eSpecifications\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"3\"\u003eDocuments\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"4\"\u003eShipping Information\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"5\"\u003eWhy Buy From Ai-Paipai?\u003c\/button\u003e\n  \u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel is-active\" data-fx-panel=\"0\"\u003e\n\u003cdiv style=\"border:2px solid #2b6cb0;background:#f0f7ff;padding:14px 18px;margin:0 0 18px;border-radius:8px;\"\u003e\n\u003ch3 style=\"margin:0 0 6px;color:#2b6cb0;\"\u003e✅ Authorized Distributor — Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.)\u003c\/h3\u003e\n\u003cp style=\"margin:0;font-size:14px;\"\u003eThis product is supplied by an \u003cb\u003eauthorized distributor\u003c\/b\u003e of the original brand.\nWe provide \u003cb\u003elocal technical support, pre-installed SDK \/ mirror images, and OEM \/ ODM customization\u003c\/b\u003e, plus fast global shipping.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cp\u003e\u003cspan\u003eAIBOX PRO is a compact host designed for edge large model deployment. It supports LLM, VLM, AI Agent, and multimodal large model implementation, while also remaining compatible with traditional algorithms such as CNN and RNN. The device adopts a heterogeneous modular architecture featuring a main controller plus an independent AI coprocessor, both designed as modules. This allows flexible selection of modules with different computing power and memory specifications based on application requirements. The device integrates CAN-FD and RS485 industrial interfaces, making it suitable for both general AI and industrial intelligence deployment needs.\u003c\/span\u003e\u003c\/p\u003e\n\u003ch2 style=\"font-size: 25px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eDual-Core Design for Multi-Task Processing\u003c\/li\u003e\n\u003cli\u003ePrimary Module 8K Codec, Multi-Channel 4K Processing\u003c\/li\u003e\n\u003cli\u003eHigh-Compute Modules for Multi-Scenario Needs\u003c\/li\u003e\n\u003cli\u003eMillisecond-Level Low Latency\u003c\/li\u003e\n\u003cli\u003eOnboard PCIe Interface for Storage Expansion\u003c\/li\u003e\n\u003cli\u003eFull Aluminum Alloy Shell\u003c\/li\u003e\n\u003cli\u003eRich Expansion Interfaces\u003c\/li\u003e\n\u003cli\u003eProvides Development Materials\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 25px;\"\u003e\u003cstrong\u003eProduct Overview\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/1_05_bd2f2808-fb47-404c-828b-002cb9a97d20.jpg?v=1782185811\" alt=\"\"\u003e\u003c\/p\u003e\n\u003ch2 style=\"font-size: 25px;\"\u003e\u003cstrong\u003eSpecifications\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/1_01_1.jpg?v=1785227125\" alt=\"\"\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/1_02_1.jpg?v=1785227140\" alt=\"\"\u003e\u003c\/p\u003e\n\u003chr\u003e\n\u003ch2\u003e\n  \u003c\/h2\u003e\n\u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"1\"\u003e\n    \u003ch3\u003eShipping list\u003c\/h3\u003e\n    \u003cul\u003e\n      \u003cli\u003eMain unit × 1\u003c\/li\u003e\n      \u003cli\u003ePower adapter \/ cable (region plug on request) × 1\u003c\/li\u003e\n      \u003cli\u003eAccessories vary by configuration — contact us for the exact included list.\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"2\"\u003e\n    \u003cp class=\"fx-note\"\u003eDetailed specifications are listed on the product images. Contact Ai-Paipai technical support for the full datasheet (PDF) and manufacturer documentation.\u003c\/p\u003e\n  \u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"3\"\u003e\n        \u003cdiv class=\"fx-docs\"\u003e\n      \u003cdiv class=\"fx-doc\"\u003e\n\u003cspan\u003eProduct tutorials\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-doc\"\u003e\n\u003cspan\u003eProduct datasheet\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-doc\"\u003e\n\u003cspan\u003eSDK software and firmware files\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e\n\u003c\/div\u003e\n    \u003c\/div\u003e\n    \u003cp class=\"fx-note\"\u003eDocument links will be replaced with the official Firefly resource URLs on request.\u003c\/p\u003e\n  \u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"4\"\u003e\n        \u003cp\u003e\u003cb\u003eOur cooperating carriers:\u003c\/b\u003e FedEx, DHL, UPS, SF Express\u003c\/p\u003e\n    \u003ch3\u003eDelivery Area And Cost\u003c\/h3\u003e\n    \u003cdiv class=\"fx-scroll\"\u003e\n      \u003ctable class=\"fx-table\"\u003e\n        \u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eCountry\/Region\u003c\/th\u003e\n\u003cth\u003e0–2kg\u003c\/th\u003e\n\u003cth\u003e2–3kg\u003c\/th\u003e\n\u003cth\u003e3–4kg\u003c\/th\u003e\n\u003cth\u003e4–5kg\u003c\/th\u003e\n\u003cth\u003e5–6kg\u003c\/th\u003e\n\u003cth\u003e6–7kg\u003c\/th\u003e\n\u003cth\u003e7–8kg\u003c\/th\u003e\n\u003cth\u003e8–9kg\u003c\/th\u003e\n\u003cth\u003e9–10kg\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n        \u003ctbody\u003e\n          \u003ctr\u003e\n\u003ctd\u003eJapan, Taiwan, Hong Kong, Macau\u003c\/td\u003e\n\u003ctd\u003e$15\u003c\/td\u003e\n\u003ctd\u003e$20\u003c\/td\u003e\n\u003ctd\u003e$25\u003c\/td\u003e\n\u003ctd\u003e$30\u003c\/td\u003e\n\u003ctd\u003e$35\u003c\/td\u003e\n\u003ctd\u003e$40\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$50\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eSingapore, Thailand, Malaysia\u003c\/td\u003e\n\u003ctd\u003e$20\u003c\/td\u003e\n\u003ctd\u003e$25\u003c\/td\u003e\n\u003ctd\u003e$30\u003c\/td\u003e\n\u003ctd\u003e$35\u003c\/td\u003e\n\u003ctd\u003e$40\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$50\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003ctd\u003e$60\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eIndonesia, Philippines\u003c\/td\u003e\n\u003ctd\u003e$25\u003c\/td\u003e\n\u003ctd\u003e$30\u003c\/td\u003e\n\u003ctd\u003e$40\u003c\/td\u003e\n\u003ctd\u003e$50\u003c\/td\u003e\n\u003ctd\u003e$60\u003c\/td\u003e\n\u003ctd\u003e$70\u003c\/td\u003e\n\u003ctd\u003e$80\u003c\/td\u003e\n\u003ctd\u003e$85\u003c\/td\u003e\n\u003ctd\u003e$95\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eSouth Korea\u003c\/td\u003e\n\u003ctd\u003e$25\u003c\/td\u003e\n\u003ctd\u003e$35\u003c\/td\u003e\n\u003ctd\u003e$35\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003ctd\u003e$65\u003c\/td\u003e\n\u003ctd\u003e$65\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eUnited States, Australia, New Zealand, Canada, UK, and most of Western Europe\u003c\/td\u003e\n\u003ctd\u003e$30\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003ctd\u003e$65\u003c\/td\u003e\n\u003ctd\u003e$75\u003c\/td\u003e\n\u003ctd\u003e$85\u003c\/td\u003e\n\u003ctd\u003e$95\u003c\/td\u003e\n\u003ctd\u003e$105\u003c\/td\u003e\n\u003ctd\u003e$115\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eOther regions (Eastern Europe, Middle East, Latin America, etc.)\u003c\/td\u003e\n\u003ctd\u003e$50\u003c\/td\u003e\n\u003ctd\u003e$65\u003c\/td\u003e\n\u003ctd\u003e$80\u003c\/td\u003e\n\u003ctd\u003e$95\u003c\/td\u003e\n\u003ctd\u003e$110\u003c\/td\u003e\n\u003ctd\u003e$125\u003c\/td\u003e\n\u003ctd\u003e$135\u003c\/td\u003e\n\u003ctd\u003e$150\u003c\/td\u003e\n\u003ctd\u003e$165\u003c\/td\u003e\n\u003c\/tr\u003e\n        \u003c\/tbody\u003e\n      \u003c\/table\u003e\n    \u003c\/div\u003e\n    \u003cp class=\"fx-note\"\u003eShipping time is for reference only; the actual situation shall prevail.\u003c\/p\u003e\n  \u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"5\"\u003e\n    Why Buy From Ai-Paipai?\n\u003cul\u003e\n\u003cli\u003e\n\u003cb\u003eAuthorized \u0026amp; Genuine\u003c\/b\u003e — sourced directly from brand-approved channels.\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eLocal Engineering Support\u003c\/b\u003e — datasheets, SDKs, and pre-flashed images in English and Chinese.\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eOEM \/ ODM \u0026amp; FPGA Customization\u003c\/b\u003e — tailor specs, enclosures, and BSP for your project.\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eOne-Stop Sourcing\u003c\/b\u003e — Firefly + youyeetoo + our own FPGA \/ edge lineup in one store.\u003c\/li\u003e\n\u003c\/ul\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e\n\n\u003cstyle\u003e\n  .fx-tabs{margin:24px 0;border:1px solid #e5e7eb;border-radius:10px;overflow:hidden;background:#fff}\n  .fx-tablist{display:flex;flex-wrap:wrap;gap:0;border-bottom:1px solid #e5e7eb;background:#f8fafc}\n  .fx-tab{flex:1 1 auto;min-width:120px;padding:14px 16px;border:0;background:transparent;cursor:pointer;font:600 14px\/1.3 inherit;color:#475569;border-bottom:3px solid transparent;transition:.18s}\n  .fx-tab:hover{color:#0f172a;background:#eef2f7}\n  .fx-tab.is-active{color:#0f172a;border-bottom-color:#2563eb;background:#fff}\n  .fx-panel{display:none;padding:22px 24px}\n  .fx-panel.is-active{display:block}\n  .fx-panel h3{font-size:16px;margin:22px 0 8px;font-weight:700}\n  .fx-panel h3:first-child{margin-top:0}\n  .fx-panel p{margin:10px 0;line-height:1.65}\n  .fx-panel ul{margin:10px 0;padding-left:22px}\n  .fx-panel li{margin:6px 0;line-height:1.6}\n  .fx-auth{background:#f0fdf4;border:1px solid #bbf7d0;border-radius:8px;padding:12px 14px;margin:0 0 16px;font-size:14px;line-height:1.6}\n  .fx-specs{border-top:1px solid #eef2f7}\n  .fx-spec{display:grid;grid-template-columns:230px 1fr;gap:16px;padding:12px 4px;border-bottom:1px solid #eef2f7}\n  .fx-k{font-weight:700;color:#334155}\n  .fx-v{color:#475569}\n  .fx-docs{display:flex;flex-direction:column;gap:10px}\n  .fx-doc{display:flex;justify-content:space-between;align-items:center;gap:12px;padding:12px 14px;border:1px solid #e5e7eb;border-radius:8px}\n  .fx-doc a{color:#2563eb;font-weight:700;text-decoration:none}\n  .fx-doc a:hover{text-decoration:underline}\n  .fx-scroll{overflow-x:auto}\n  .fx-table{border-collapse:collapse;width:100%;min-width:760px;font-size:13px}\n  .fx-table th,.fx-table td{border:1px solid #e5e7eb;padding:8px 10px;text-align:left}\n  .fx-table th{background:#f8fafc;font-weight:700}\n  .fx-note{color:#64748b;font-size:13px;margin-top:12px}\n  @media (max-width:749px){.fx-spec{grid-template-columns:1fr;gap:4px}.fx-tab{min-width:50%;flex:1 1 50%}.fx-panel{padding:16px}}\n\u003c\/style\u003e\n\n\u003cscript\u003e\n  (function () {\n    var roots = document.querySelectorAll('[data-fx-tabs]');\n    roots.forEach(function (root) {\n      var tabs = root.querySelectorAll('[data-fx-tab]');\n      var panels = root.querySelectorAll('[data-fx-panel]');\n      tabs.forEach(function (t) {\n        t.addEventListener('click', function () {\n          var i = t.getAttribute('data-fx-tab');\n          tabs.forEach(function (x) { x.classList.toggle('is-active', x === t); });\n          panels.forEach(function (p) { p.classList.toggle('is-active', p.getAttribute('data-fx-panel') === i); });\n        });\n      });\n    });\n  })();\n\u003c\/script\u003e","brand":"Firefly","offers":[{"title":"RK3588(8G+64G) + RM1828*1","offer_id":48422465536258,"sku":"firefly-aibox-pro-edge-computing-computer-46998054797396","price":899.0,"currency_code":"USD","in_stock":true},{"title":"RK3588(8G+64G) + RM1828*2","offer_id":48422465569026,"sku":"firefly-aibox-pro-edge-computing-computer-47407602794580","price":1149.0,"currency_code":"USD","in_stock":true},{"title":"RK3588(16G+256G) + RM1828*1","offer_id":48422465601794,"sku":"firefly-aibox-pro-edge-computing-computer-47256929534036","price":1149.0,"currency_code":"USD","in_stock":true},{"title":"RK3588(16G+256G) + RM1828*2","offer_id":48422465634562,"sku":"firefly-aibox-pro-edge-computing-computer-47407602827348","price":1409.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0837\/5953\/0242\/files\/3034a1133efe01daba919094b70c6310.jpg?v=1788244274"},{"product_id":"aibox-k3-risc-v-edge-mini-pc","title":"AIBOX-K3 RISC-V Edge Mini PC","description":"\u003cp class=\"geo-summary\" style=\"font-size:1rem;line-height:1.65;margin:0 0 1.25rem;padding:0 0 1rem;border-bottom:1px solid #e5e7eb;color:#1f2937\"\u003e\u003cstrong\u003eAIBOX-K3 RISC-V Edge Mini PC\u003c\/strong\u003e is a Firefly product sold by Ai-Paipai. Key specifications — Soc: SpacemiT Key Stone K3 · Ai performance: 8-core A100 delivers 60TOPS AI computing power… · Ram: 8GB\/16GB\/32GB LPDDR5 · Storage: 128GB\/256GB\/512GB UFS2.2 · Ethernet: 2 × Gigabit Ethernet (1000Mbps\/RJ45). Typical applications: edge AI inference and industrial automation. Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.) is an authorized distributor providing local technical support, pre-installed SDK \/ OS images, OEM \/ ODM customization, and worldwide shipping.\u003c\/p\u003e \u003c!-- Firefly product tabs --\u003e \u003cdiv class=\"fx-tabs\" data-fx-tabs\u003e \u003cdiv class=\"fx-tablist\" role=\"tablist\"\u003e \u003cbutton class=\"fx-tab is-active\" role=\"tab\" data-fx-tab=\"0\"\u003eDescription\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"1\"\u003eWhat's Included\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"2\"\u003eSpecifications\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"3\"\u003eDocuments\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"4\"\u003eShipping Information\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"5\"\u003eWhy Buy From Ai-Paipai?\u003c\/button\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel is-active\" data-fx-panel=\"0\"\u003e \u003cdiv style=\"border:2px solid #2b6cb0;background:#f0f7ff;padding:14px 18px;margin:0 0 18px;border-radius:8px;\"\u003e \u003ch3 style=\"margin:0 0 6px;color:#2b6cb0;\"\u003e✅ Authorized Distributor — Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.)\u003c\/h3\u003e \u003cp style=\"margin:0;font-size:14px;\"\u003eThis product is supplied by an \u003cb\u003eauthorized distributor\u003c\/b\u003e of the original brand.\nWe provide \u003cb\u003elocal technical support, pre-installed SDK \/ mirror images, and OEM \/ ODM customization\u003c\/b\u003e, plus fast global shipping.\u003c\/p\u003e \u003c\/div\u003e \u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/1_3_eb2909d4-cf65-4093-8dcd-96bbe4757768.jpg?v=1778661906\" alt=\"\"\u003e\u003c\/p\u003e \u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/1_02.jpg?v=1778495070\" alt=\"\"\u003e\u003c\/p\u003e \u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/1_03.jpg?v=1778495098\" alt=\"\"\u003e\u003c\/p\u003e \u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/1_04.jpg?v=1778495200\" alt=\"\"\u003e\u003c\/p\u003e \u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/1_05.jpg?v=1778495236\" alt=\"\"\u003e\u003c\/p\u003e \u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/1_06.jpg?v=1778495318\" alt=\"\"\u003e\u003c\/p\u003e \u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/2_3_4a59bd36-abba-4f0f-b460-857ec71476b2.jpg?v=1778661925\" alt=\"\"\u003e\u003c\/p\u003e \u003chr\u003e \u003ch2\u003e \u003c\/h2\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"1\"\u003e \u003ch3\u003eShipping list\u003c\/h3\u003e \u003cul\u003e \u003cli\u003eMain unit × 1\u003c\/li\u003e \u003cli\u003ePower adapter \/ cable (region plug on request) × 1\u003c\/li\u003e \u003cli\u003eAccessories vary by configuration — contact us for the exact included list.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"2\"\u003e \u003cdiv class=\"fx-specs\"\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eAi performance\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e8-core A100 delivers 60TOPS AI computing power (SquareINT4), supporting BF16, FP16, FP8, INT8, INT4 and other data formats. Equipped with RVV vector instruction set, native FP8 inference and multi-modal algorithm acceleration, it supports 30B local models, with inference performance exceeding 10Tokens\/S@30B, and adapts to various AI algorithms and model deployment.\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eConsole\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 × Console (Debug serial)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSoc\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eSpacemiT Key Stone K3\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eCpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e8-core X100 64-bit RISC-V AI Processor, max main frequency 2.4GHz, 130KDMIPS general computing power, full RVA23 Profile support, single- core Specint2006\u0026gt;9.0\/GHz, equivalent to ARM-A76\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eGpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eIntegrated 3D graphics engine, supporting Vulkan 1.3, OpenCL 3.0, OpenGL ES 1.1\/3.2, EGL 1.5\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eRam\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e8GB\/16GB\/32GB LPDDR5\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eStorage\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e128GB\/256GB\/512GB UFS2.2\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eStorage expansion\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 × M.2 (PCIe3.0x4 lane, support for 2242\/2280 specification PCIe NVMe SSD; located inside the computer)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eCodecs\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eVideo decoding: 4K@120fps H.264\/VP9\nVideo encoding: 4K@60fps H.264\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eDC 12V\/5A (5.5 × 2.1mm, supporting 9V~20V wide voltage input)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eOs\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eUbuntu 26.04, Buildroot Linux with QT GUI, Fedora, Bianbu OS, Deepin, OpenKylin, OpenHarmony 6.1, OpenEuler\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eDimension\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e93.4mm × 93.4mm × 50.0mm\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eWeight\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e≈ 500g\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEnvironment\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eOperating Temperature: -20℃~60℃, Storage Temperature: -20℃~70℃, Operating Humidity: 10%~90%RH (No condensation)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEthernet\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 × Gigabit Ethernet (1000Mbps\/RJ45)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eUsb\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 × USB3.0 (Max: 1A), 1 × USB3.0 DRD (Type-C, includes USB2.0 OTG)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eButton\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 × Power, 1 × Boot\u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"3\"\u003e \u003cdiv class=\"fx-docs\"\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct tutorials\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct datasheet\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eSDK software and firmware files\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eDocument links will be replaced with the official Firefly resource URLs on request.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"4\"\u003e \u003cp\u003e\u003cb\u003eOur cooperating carriers:\u003c\/b\u003e FedEx, DHL, UPS, SF Express\u003c\/p\u003e \u003ch3\u003eDelivery Area And Cost\u003c\/h3\u003e \u003cdiv class=\"fx-scroll\"\u003e \u003ctable class=\"fx-table\"\u003e \u003cthead\u003e\u003ctr\u003e \u003cth\u003eCountry\/Region\u003c\/th\u003e \u003cth\u003e0–2kg\u003c\/th\u003e \u003cth\u003e2–3kg\u003c\/th\u003e \u003cth\u003e3–4kg\u003c\/th\u003e \u003cth\u003e4–5kg\u003c\/th\u003e \u003cth\u003e5–6kg\u003c\/th\u003e \u003cth\u003e6–7kg\u003c\/th\u003e \u003cth\u003e7–8kg\u003c\/th\u003e \u003cth\u003e8–9kg\u003c\/th\u003e \u003cth\u003e9–10kg\u003c\/th\u003e \u003c\/tr\u003e\u003c\/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd\u003eJapan, Taiwan, Hong Kong, Macau\u003c\/td\u003e \u003ctd\u003e$15\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSingapore, Thailand, Malaysia\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eIndonesia, Philippines\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003ctd\u003e$70\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSouth Korea\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eUnited States, Australia, New Zealand, Canada, UK, and most of Western Europe\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$75\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$105\u003c\/td\u003e \u003ctd\u003e$115\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eOther regions (Eastern Europe, Middle East, Latin America, etc.)\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$110\u003c\/td\u003e \u003ctd\u003e$125\u003c\/td\u003e \u003ctd\u003e$135\u003c\/td\u003e \u003ctd\u003e$150\u003c\/td\u003e \u003ctd\u003e$165\u003c\/td\u003e \u003c\/tr\u003e \u003c\/tbody\u003e \u003c\/table\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eShipping time is for reference only; the actual situation shall prevail.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"5\"\u003e\n Why Buy From Ai-Paipai? \u003cul\u003e \u003cli\u003e \u003cb\u003eAuthorized \u0026amp; Genuine\u003c\/b\u003e — sourced directly from brand-approved channels.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eLocal Engineering Support\u003c\/b\u003e — datasheets, SDKs, and pre-flashed images in English and Chinese.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOEM \/ ODM \u0026amp; FPGA Customization\u003c\/b\u003e — tailor specs, enclosures, and BSP for your project.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOne-Stop Sourcing\u003c\/b\u003e — Firefly + youyeetoo + our own FPGA \/ edge lineup in one store.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cstyle\u003e.fx-tabs{margin:24px 0;border:1px solid #e5e7eb;border-radius:10px;overflow:hidden;background:#fff}.fx-tablist{display:flex;flex-wrap:wrap;gap:0;border-bottom:1px solid #e5e7eb;background:#f8fafc}.fx-tab{flex:1 1 auto;min-width:120px;padding:14px 16px;border:0;background:transparent;cursor:pointer;font:600 14px\/1.3 inherit;color:#475569;border-bottom:3px solid transparent;transition:.18s}.fx-tab:hover{color:#0f172a;background:#eef2f7}.fx-tab.is-active{color:#0f172a;border-bottom-color:#2563eb;background:#fff}.fx-panel{display:none;padding:22px 24px}.fx-panel.is-active{display:block}.fx-panel h3{font-size:16px;margin:22px 0 8px;font-weight:700}.fx-panel h3:first-child{margin-top:0}.fx-panel p{margin:10px 0;line-height:1.65}.fx-panel ul{margin:10px 0;padding-left:22px}.fx-panel li{margin:6px 0;line-height:1.6}.fx-auth{background:#f0fdf4;border:1px solid #bbf7d0;border-radius:8px;padding:12px 14px;margin:0 0 16px;font-size:14px;line-height:1.6}.fx-specs{border-top:1px solid #eef2f7}.fx-spec{display:grid;grid-template-columns:230px 1fr;gap:16px;padding:12px 4px;border-bottom:1px solid #eef2f7}.fx-k{font-weight:700;color:#334155}.fx-v{color:#475569}.fx-docs{display:flex;flex-direction:column;gap:10px}.fx-doc{display:flex;justify-content:space-between;align-items:center;gap:12px;padding:12px 14px;border:1px solid #e5e7eb;border-radius:8px}.fx-doc a{color:#2563eb;font-weight:700;text-decoration:none}.fx-doc a:hover{text-decoration:underline}.fx-scroll{overflow-x:auto}.fx-table{border-collapse:collapse;width:100%;min-width:760px;font-size:13px}.fx-table th,.fx-table td{border:1px solid #e5e7eb;padding:8px 10px;text-align:left}.fx-table th{background:#f8fafc;font-weight:700}.fx-note{color:#64748b;font-size:13px;margin-top:12px}\n @media (max-width:749px){.fx-spec{grid-template-columns:1fr;gap:4px}.fx-tab{min-width:50%;flex:1 1 50%}.fx-panel{padding:16px}} \u003c\/style\u003e \u003cscript\u003e\n (function () {\n var roots = document.querySelectorAll('[data-fx-tabs]');\n roots.forEach(function (root) {\n var tabs = root.querySelectorAll('[data-fx-tab]');\n var panels = root.querySelectorAll('[data-fx-panel]');\n tabs.forEach(function (t) {\n t.addEventListener('click', function () {\n var i = t.getAttribute('data-fx-tab');\n tabs.forEach(function (x) { x.classList.toggle('is-active', x === t); });\n panels.forEach(function (p) { p.classList.toggle('is-active', p.getAttribute('data-fx-panel') === i); });\n });\n });\n });\n })(); \u003c\/script\u003e","brand":"Firefly","offers":[{"title":"8G+128G","offer_id":48422466519298,"sku":"firefly-aibox-k3-risc-v-edge-mini-pc-46857894789204","price":509.0,"currency_code":"USD","in_stock":true},{"title":"32G+128G","offer_id":48422466552066,"sku":"firefly-aibox-k3-risc-v-edge-mini-pc-46857894821972","price":969.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0837\/5953\/0242\/files\/3589.png?v=1788244279"},{"product_id":"aibox-1684-computing-box-17-6t-deep-learning-multi-channel-video-decoder-bmnnsdk2-computing-bm1684","title":"AIBOX-1684 AI Edge Computing Industrial PC","description":"\u003cp class=\"geo-summary\" style=\"font-size:1rem;line-height:1.65;margin:0 0 1.25rem;padding:0 0 1rem;border-bottom:1px solid #e5e7eb;color:#1f2937\"\u003e\u003cstrong\u003eAIBOX-1684 AI Edge Computing Industrial PC\u003c\/strong\u003e is a Firefly product sold by Ai-Paipai. Key specifications — Soc: SOPHON BM1684 · Ram: 6GB\/12GB\/16GB LPDDR4\/LPDDR4X · Storage: 32GB\/64GB\/128GB eMMC, 1 × TF Card · Ethernet: 2 × Gigabit Ethernet (1000Mbps\/RJ45) · Software support: Traditional network architectures such as CNN, RNN, and…. Typical applications: edge AI inference, machine vision and industrial automation. Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.) is an authorized distributor providing local technical support, pre-installed SDK \/ OS images, OEM \/ ODM customization, and worldwide shipping.\u003c\/p\u003e \u003c!-- Firefly product tabs --\u003e \u003cdiv class=\"fx-tabs\" data-fx-tabs\u003e \u003cdiv class=\"fx-tablist\" role=\"tablist\"\u003e \u003cbutton class=\"fx-tab is-active\" role=\"tab\" data-fx-tab=\"0\"\u003eDescription\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"1\"\u003eWhat's Included\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"2\"\u003eSpecifications\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"3\"\u003eDocuments\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"4\"\u003eShipping Information\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"5\"\u003eWhy Buy From Ai-Paipai?\u003c\/button\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel is-active\" data-fx-panel=\"0\"\u003e \u003cdiv style=\"border:2px solid #2b6cb0;background:#f0f7ff;padding:14px 18px;margin:0 0 18px;border-radius:8px;\"\u003e \u003ch3 style=\"margin:0 0 6px;color:#2b6cb0;\"\u003e✅ Authorized Distributor — Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.)\u003c\/h3\u003e \u003cp style=\"margin:0;font-size:14px;\"\u003eThis product is supplied by an \u003cb\u003eauthorized distributor\u003c\/b\u003e of the original brand.\nWe provide \u003cb\u003elocal technical support, pre-installed SDK \/ mirror images, and OEM \/ ODM customization\u003c\/b\u003e, plus fast global shipping.\u003c\/p\u003e \u003c\/div\u003e \u003cp\u003eThe AIBOX-1684, powered by SOPHON's BM1684 AI processor, delivers up to 17.6TOPS INT8 computing power, supporting 32-channel 1080P H.264 decoding and 2-channel encoding - ideal for smart surveillance, AI education, edge computing, and data security applications.\u003c\/p\u003e \u003cul\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-1684X_AIBOX-1684_Specification_EN.pdf?v=1752722974\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Wiki: \u003ca href=\"https:\/\/wiki.t-firefly.com\/en\/AIBOX-1684\/index.html\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e \u003cul\u003e \u003cli\u003e \u003cstrong\u003e17.6 TOPS AI Processor BM1684:\u003c\/strong\u003e The BM1684 AI processor by SOPHON features an octa-core ARM Cortex-A53 (up to 2.3 GHz) and a TPU acceleration engine, delivering 17.6 TOPS INT8, 2.2 TFLOPS FP32, and 35.2 TFLOPS FP16 (with Winograd) and supports major AI frameworks.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eMulti-Channel Video AI Processing Performance: \u003c\/strong\u003eThe AIBOX embedded PC delivers high-performance video processing with 32-channel 1080P@30fps H.264 decoding, dual-channel 1080P@25fps encoding, and MJPEG support up to 1080P@480fps—ideal for AI vision, smart surveillance, and edge computing solutions.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eAbundant Algorithms: \u003c\/strong\u003eThe AIBOX embedded PC supports multi-algorithm deployment including person\/vehicle\/object detection, video structuring, and behavior analysis, with high security \u0026amp; reliability for flexible integration into smart city, retail analytics, and industrial vision applications.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eStrong Network Communication Capability:\u003c\/strong\u003e The AIBOX embedded PC is equipped with dual 1000Mbps Ethernet ports to ensure high-speed and stable network communication, meeting the needs of various application scenarios.\u003c\/li\u003e \u003c\/ul\u003e \u003cp\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-1684-__04.jpg?v=1730959121\"\u003e\u003c\/p\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eHardware Overview\u003c\/strong\u003e\u003c\/h2\u003e \u003cp\u003e\u003cstrong\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-1684X.webp?v=1752722845\" alt=\"\"\u003e\u003c\/strong\u003e\u003c\/p\u003e \u003chr\u003e \u003ch2\u003e \u003c\/h2\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"1\"\u003e \u003ch3\u003eShipping list\u003c\/h3\u003e \u003cul\u003e \u003cli\u003eMain unit × 1\u003c\/li\u003e \u003cli\u003ePower adapter \/ cable (region plug on request) × 1\u003c\/li\u003e \u003cli\u003eAccessories vary by configuration — contact us for the exact included list.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"2\"\u003e \u003cdiv class=\"fx-specs\"\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSoc\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eSOPHON BM1684\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eCpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eHigh-performance octa-core ARM A53, 12nm lithography process, frequency up to 2.3 GHz\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eTpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e17.6TOPS (INT8), 2.2TOPS (FP32),35.2TOPS (INT8, enable winograd)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eVpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e32-channel H.265\/H.264 1080P@30fps video decoding\n2-channel H.265\/H.264 1080P@25fps video encoding\nMJPEG image encoding\/decoding can reach 1080P@480fps\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eRam\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e6GB\/12GB\/16GB LPDDR4\/LPDDR4X\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eStorage\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e32GB\/64GB\/128GB eMMC, 1 × TF Card\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eDC 12V\/3A (5.5 × 2.5mm)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower consumption\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eNormal: 9.6W(12V\/800mA)\nMax: 26.4W(12V\/2200mA)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSoftware support\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eTraditional network architectures such as CNN, RNN, and LSTM; a variety of deep learning frameworks, including TensorFlow, PyTorch, MXNet, PaddlePaddle, Caffe, and ONNX, as well as custom operator development\nDocker container management technology\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eDimension\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e90.6 mm × 84.4 mm × 48.5mm\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eWeight\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e≈ 420g\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEnvironment\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eOperating temperature: -20℃~60℃,\nStorage temperature: -20℃~70℃,\nStorage humidity: 10%~90%RH (non-condensing)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEthernet\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 × Gigabit Ethernet (1000Mbps\/RJ45)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eUsb\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 × USB3.0 (Max: 1A), \n1 × Type-C (Debug serial)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eButton\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 × Power button\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eProduct tutorials\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSdk software and firmware files\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"3\"\u003e \u003cdiv class=\"fx-docs\"\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct tutorials\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct datasheet\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eSDK software and firmware files\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eDocument links will be replaced with the official Firefly resource URLs on request.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"4\"\u003e \u003cp\u003e\u003cb\u003eOur cooperating carriers:\u003c\/b\u003e FedEx, DHL, UPS, SF Express\u003c\/p\u003e \u003ch3\u003eDelivery Area And Cost\u003c\/h3\u003e \u003cdiv class=\"fx-scroll\"\u003e \u003ctable class=\"fx-table\"\u003e \u003cthead\u003e\u003ctr\u003e \u003cth\u003eCountry\/Region\u003c\/th\u003e \u003cth\u003e0–2kg\u003c\/th\u003e \u003cth\u003e2–3kg\u003c\/th\u003e \u003cth\u003e3–4kg\u003c\/th\u003e \u003cth\u003e4–5kg\u003c\/th\u003e \u003cth\u003e5–6kg\u003c\/th\u003e \u003cth\u003e6–7kg\u003c\/th\u003e \u003cth\u003e7–8kg\u003c\/th\u003e \u003cth\u003e8–9kg\u003c\/th\u003e \u003cth\u003e9–10kg\u003c\/th\u003e \u003c\/tr\u003e\u003c\/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd\u003eJapan, Taiwan, Hong Kong, Macau\u003c\/td\u003e \u003ctd\u003e$15\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSingapore, Thailand, Malaysia\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eIndonesia, Philippines\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003ctd\u003e$70\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSouth Korea\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eUnited States, Australia, New Zealand, Canada, UK, and most of Western Europe\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$75\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$105\u003c\/td\u003e \u003ctd\u003e$115\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eOther regions (Eastern Europe, Middle East, Latin America, etc.)\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$110\u003c\/td\u003e \u003ctd\u003e$125\u003c\/td\u003e \u003ctd\u003e$135\u003c\/td\u003e \u003ctd\u003e$150\u003c\/td\u003e \u003ctd\u003e$165\u003c\/td\u003e \u003c\/tr\u003e \u003c\/tbody\u003e \u003c\/table\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eShipping time is for reference only; the actual situation shall prevail.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"5\"\u003e\n Why Buy From Ai-Paipai? \u003cul\u003e \u003cli\u003e \u003cb\u003eAuthorized \u0026amp; Genuine\u003c\/b\u003e — sourced directly from brand-approved channels.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eLocal Engineering Support\u003c\/b\u003e — datasheets, SDKs, and pre-flashed images in English and Chinese.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOEM \/ ODM \u0026amp; FPGA Customization\u003c\/b\u003e — tailor specs, enclosures, and BSP for your project.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOne-Stop Sourcing\u003c\/b\u003e — Firefly + youyeetoo + our own FPGA \/ edge lineup in one store.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cstyle\u003e.fx-tabs{margin:24px 0;border:1px solid #e5e7eb;border-radius:10px;overflow:hidden;background:#fff}.fx-tablist{display:flex;flex-wrap:wrap;gap:0;border-bottom:1px solid #e5e7eb;background:#f8fafc}.fx-tab{flex:1 1 auto;min-width:120px;padding:14px 16px;border:0;background:transparent;cursor:pointer;font:600 14px\/1.3 inherit;color:#475569;border-bottom:3px solid transparent;transition:.18s}.fx-tab:hover{color:#0f172a;background:#eef2f7}.fx-tab.is-active{color:#0f172a;border-bottom-color:#2563eb;background:#fff}.fx-panel{display:none;padding:22px 24px}.fx-panel.is-active{display:block}.fx-panel h3{font-size:16px;margin:22px 0 8px;font-weight:700}.fx-panel h3:first-child{margin-top:0}.fx-panel p{margin:10px 0;line-height:1.65}.fx-panel ul{margin:10px 0;padding-left:22px}.fx-panel li{margin:6px 0;line-height:1.6}.fx-auth{background:#f0fdf4;border:1px solid #bbf7d0;border-radius:8px;padding:12px 14px;margin:0 0 16px;font-size:14px;line-height:1.6}.fx-specs{border-top:1px solid #eef2f7}.fx-spec{display:grid;grid-template-columns:230px 1fr;gap:16px;padding:12px 4px;border-bottom:1px solid #eef2f7}.fx-k{font-weight:700;color:#334155}.fx-v{color:#475569}.fx-docs{display:flex;flex-direction:column;gap:10px}.fx-doc{display:flex;justify-content:space-between;align-items:center;gap:12px;padding:12px 14px;border:1px solid #e5e7eb;border-radius:8px}.fx-doc a{color:#2563eb;font-weight:700;text-decoration:none}.fx-doc a:hover{text-decoration:underline}.fx-scroll{overflow-x:auto}.fx-table{border-collapse:collapse;width:100%;min-width:760px;font-size:13px}.fx-table th,.fx-table td{border:1px solid #e5e7eb;padding:8px 10px;text-align:left}.fx-table th{background:#f8fafc;font-weight:700}.fx-note{color:#64748b;font-size:13px;margin-top:12px}\n @media (max-width:749px){.fx-spec{grid-template-columns:1fr;gap:4px}.fx-tab{min-width:50%;flex:1 1 50%}.fx-panel{padding:16px}} \u003c\/style\u003e \u003cscript\u003e\n (function () {\n var roots = document.querySelectorAll('[data-fx-tabs]');\n roots.forEach(function (root) {\n var tabs = root.querySelectorAll('[data-fx-tab]');\n var panels = root.querySelectorAll('[data-fx-panel]');\n tabs.forEach(function (t) {\n t.addEventListener('click', function () {\n var i = t.getAttribute('data-fx-tab');\n tabs.forEach(function (x) { x.classList.toggle('is-active', x === t); });\n panels.forEach(function (p) { p.classList.toggle('is-active', p.getAttribute('data-fx-panel') === i); });\n });\n });\n });\n })(); \u003c\/script\u003e","brand":"Firefly","offers":[{"title":"12G RAM+32GROM","offer_id":48422467731714,"sku":"firefly-aibox-1684-computing-box-17-6t-deep-learning-multi-channel-video-decoder-bmnnsdk2-computing-bm1684-41682489901140","price":489.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0837\/5953\/0242\/files\/AIBOX-1684-800800_2_79efaa3b-7f4c-4f30-9543-4d1c73a44e96.jpg?v=1788244291"},{"product_id":"aibox-186-artificial-intelligence-box-6t-large-model-privatization-deployment-deep-learning-computing-cv186ah","title":"AIBOX-186 AI Edge Computing Embedded PC","description":"\u003cp class=\"geo-summary\" style=\"font-size:1rem;line-height:1.65;margin:0 0 1.25rem;padding:0 0 1rem;border-bottom:1px solid #e5e7eb;color:#1f2937\"\u003e\u003cstrong\u003eAIBOX-186 AI Edge Computing Embedded PC\u003c\/strong\u003e is a Firefly product sold by Ai-Paipai. Key specifications — Soc: SOPHON CV186AH · Ram: 4GB LPDDR4 (4GB\/8GB\/16GB optional) · Storage: 32GB eMMC (32GB\/64GB\/128GB\/256GB optional) · Ethernet: 2 x 1000Mbps Ethernet · Video output: 1 x HDMI2.0 (4K@60fps. Typical applications: edge AI inference, machine vision and industrial automation. Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.) is an authorized distributor providing local technical support, pre-installed SDK \/ OS images, OEM \/ ODM customization, and worldwide shipping.\u003c\/p\u003e \u003c!-- Firefly product tabs --\u003e \u003cdiv class=\"fx-tabs\" data-fx-tabs\u003e \u003cdiv class=\"fx-tablist\" role=\"tablist\"\u003e \u003cbutton class=\"fx-tab is-active\" role=\"tab\" data-fx-tab=\"0\"\u003eDescription\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"1\"\u003eWhat's Included\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"2\"\u003eSpecifications\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"3\"\u003eDocuments\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"4\"\u003eShipping Information\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"5\"\u003eWhy Buy From Ai-Paipai?\u003c\/button\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel is-active\" data-fx-panel=\"0\"\u003e \u003cdiv style=\"border:2px solid #2b6cb0;background:#f0f7ff;padding:14px 18px;margin:0 0 18px;border-radius:8px;\"\u003e \u003ch3 style=\"margin:0 0 6px;color:#2b6cb0;\"\u003e✅ Authorized Distributor — Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.)\u003c\/h3\u003e \u003cp style=\"margin:0;font-size:14px;\"\u003eThis product is supplied by an \u003cb\u003eauthorized distributor\u003c\/b\u003e of the original brand.\nWe provide \u003cb\u003elocal technical support, pre-installed SDK \/ mirror images, and OEM \/ ODM customization\u003c\/b\u003e, plus fast global shipping.\u003c\/p\u003e \u003c\/div\u003e \u003cp\u003eThe AIBOX-186 AI edge computer delivers 7.2 TOPS of processing power, enabling private deployment of mainstream large AI models for secure, customized on-device intelligence in enterprise and industrial applications.\u003c\/p\u003e \u003cul\u003e \u003cli style=\"font-weight: bold;\"\u003e \u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-1688_AIBOX-186_Specification_EN.pdf?v=1752733724\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003cbr\u003e \u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e \u003cul\u003e \u003cli\u003e \u003cstrong\u003e7.2 TOPS AI Processor CV186AH: \u003c\/strong\u003eThe CV186AH AI processor by SOPHON integrates a hexa-core ARM Cortex-A53 (1.6GHz) and a high-efficiency TPU, delivering 7.2 TOPS INT8 and 12 TOPS INT4 performance with 1.5 TFLOPS FP16\/BF16 support. Compatible with mainstream AI frameworks, it’s engineered for edge AI inference, computer vision, and embedded deep learning applications.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eMulti-channel Video AI Performance: \u003c\/strong\u003eThis high-performance AI processing box supports 16-channel 1080P H.264 decoding, 10-channel 1080P encoding, and simultaneous 16-channel HD video analysis (decoding + AI processing). Designed for intelligent video analytics, it enables real-time applications including facial recognition, license plate identification, and smart city solutions.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eStrong Network Communication Capability:\u003c\/strong\u003e The AIBOX embedded PC is equipped with dual 1000Mbps Ethernet ports to ensure high-speed and stable network communication, meeting the needs of various application scenarios.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eAll-aluminum Alloy Enclosure:\u003c\/strong\u003e The industrial-grade AI box features a rugged all-metal enclosure with aluminum alloy construction for superior thermal conduction. Its optimized grille design enables efficient airflow and heat dissipation, maintaining peak computing performance and reliability even in high-temperature environments.\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eHardware Overview\u003c\/strong\u003e\u003c\/h2\u003e \u003cp\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-1688.webp?v=1752733594\"\u003e\u003c\/p\u003e \u003chr\u003e \u003ch2\u003e \u003c\/h2\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"1\"\u003e \u003ch3\u003eShipping list\u003c\/h3\u003e \u003cul\u003e \u003cli\u003eMain unit × 1\u003c\/li\u003e \u003cli\u003ePower adapter \/ cable (region plug on request) × 1\u003c\/li\u003e \u003cli\u003eAccessories vary by configuration — contact us for the exact included list.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"2\"\u003e \u003cdiv class=\"fx-specs\"\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSoc\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eSOPHON CV186AH\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eCpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eHexa-core ARM Cortex-A53 @1.6GHz\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eTpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e7.2T@INT8, 12T@INT4, and 1.5T@FP16\/BF16 computing power\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eVpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eVideo decoding: H.264 \/ H.265 decoding (Max performance: 1920 x 1080@480FPS or 3840 x 2160 @120FPS)\nVideo encoding: H.264 \/ H.265 encoding (Max performance: 1920 x 1080@300FPS or 3840 x 2160 @75 FPS)\nImage codec: JPEG\/MJPEG Baseline codec (JPEG codec with a maximum resolution of 1080P@480 FPS)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eRam\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e4GB LPDDR4 (4GB\/8GB\/16GB optional)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eStorage\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e32GB eMMC (32GB\/64GB\/128GB\/256GB optional)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eStorage expansion\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 x M.2 (Expandable PCIe NVMe SSD(default support)\/ SATA SSD(supported after software update), supports 2242\/2260\/2280) (inside the device), 1 x TF Card\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eDC 12V\/3A(DC 5.5*2.1mm)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower consumption\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eNormal: 6W(12V\/500mA)\nMax: 10.8W(12V\/900mA)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eVideo output\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 x HDMI2.0 (4K@60fps\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eOs\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eLinux\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSoftware support\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eThe private deployment of ultra-large-scale parameter models under the Transformer architecture, including large language models such as Gemma-2B, LlaMa2-7B, ChatGLM3-6B, Qwen1.5-1.8B.\nA variety of deep learning frameworks, including TensorFlow, PyTorch, TensorRT, TFLite, PaddlePaddle, Caffe, and ONNX, as well as custom operator development\nDocker container management technology\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eDimension\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e93.4 mm × 93.4mm × 50 mm\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eWeight\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e≈ 500g\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEnvironment\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eOperating Temperature: -20℃~60℃\nStorage Temperature: -20℃~70℃\nStorage Humidity: 10%~90%RH (non-condensing)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEthernet\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 x 1000Mbps Ethernet\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eUsb\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 x USB3.0 (Current Limit: 1A)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eOther\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 x Type-C (USB 2.0 device mode only), \n1 x Console (Debug serial), \n1 x Power button, \n1 x Recovery\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eProduct tutorials\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSdk software and firmware files\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"3\"\u003e \u003cdiv class=\"fx-docs\"\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct tutorials\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct datasheet\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eSDK software and firmware files\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eDocument links will be replaced with the official Firefly resource URLs on request.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"4\"\u003e \u003cp\u003e\u003cb\u003eOur cooperating carriers:\u003c\/b\u003e FedEx, DHL, UPS, SF Express\u003c\/p\u003e \u003ch3\u003eDelivery Area And Cost\u003c\/h3\u003e \u003cdiv class=\"fx-scroll\"\u003e \u003ctable class=\"fx-table\"\u003e \u003cthead\u003e\u003ctr\u003e \u003cth\u003eCountry\/Region\u003c\/th\u003e \u003cth\u003e0–2kg\u003c\/th\u003e \u003cth\u003e2–3kg\u003c\/th\u003e \u003cth\u003e3–4kg\u003c\/th\u003e \u003cth\u003e4–5kg\u003c\/th\u003e \u003cth\u003e5–6kg\u003c\/th\u003e \u003cth\u003e6–7kg\u003c\/th\u003e \u003cth\u003e7–8kg\u003c\/th\u003e \u003cth\u003e8–9kg\u003c\/th\u003e \u003cth\u003e9–10kg\u003c\/th\u003e \u003c\/tr\u003e\u003c\/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd\u003eJapan, Taiwan, Hong Kong, Macau\u003c\/td\u003e \u003ctd\u003e$15\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSingapore, Thailand, Malaysia\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eIndonesia, Philippines\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003ctd\u003e$70\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSouth Korea\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eUnited States, Australia, New Zealand, Canada, UK, and most of Western Europe\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$75\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$105\u003c\/td\u003e \u003ctd\u003e$115\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eOther regions (Eastern Europe, Middle East, Latin America, etc.)\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$110\u003c\/td\u003e \u003ctd\u003e$125\u003c\/td\u003e \u003ctd\u003e$135\u003c\/td\u003e \u003ctd\u003e$150\u003c\/td\u003e \u003ctd\u003e$165\u003c\/td\u003e \u003c\/tr\u003e \u003c\/tbody\u003e \u003c\/table\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eShipping time is for reference only; the actual situation shall prevail.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"5\"\u003e\n Why Buy From Ai-Paipai? \u003cul\u003e \u003cli\u003e \u003cb\u003eAuthorized \u0026amp; Genuine\u003c\/b\u003e — sourced directly from brand-approved channels.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eLocal Engineering Support\u003c\/b\u003e — datasheets, SDKs, and pre-flashed images in English and Chinese.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOEM \/ ODM \u0026amp; FPGA Customization\u003c\/b\u003e — tailor specs, enclosures, and BSP for your project.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOne-Stop Sourcing\u003c\/b\u003e — Firefly + youyeetoo + our own FPGA \/ edge lineup in one store.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cstyle\u003e.fx-tabs{margin:24px 0;border:1px solid #e5e7eb;border-radius:10px;overflow:hidden;background:#fff}.fx-tablist{display:flex;flex-wrap:wrap;gap:0;border-bottom:1px solid #e5e7eb;background:#f8fafc}.fx-tab{flex:1 1 auto;min-width:120px;padding:14px 16px;border:0;background:transparent;cursor:pointer;font:600 14px\/1.3 inherit;color:#475569;border-bottom:3px solid transparent;transition:.18s}.fx-tab:hover{color:#0f172a;background:#eef2f7}.fx-tab.is-active{color:#0f172a;border-bottom-color:#2563eb;background:#fff}.fx-panel{display:none;padding:22px 24px}.fx-panel.is-active{display:block}.fx-panel h3{font-size:16px;margin:22px 0 8px;font-weight:700}.fx-panel h3:first-child{margin-top:0}.fx-panel p{margin:10px 0;line-height:1.65}.fx-panel ul{margin:10px 0;padding-left:22px}.fx-panel li{margin:6px 0;line-height:1.6}.fx-auth{background:#f0fdf4;border:1px solid #bbf7d0;border-radius:8px;padding:12px 14px;margin:0 0 16px;font-size:14px;line-height:1.6}.fx-specs{border-top:1px solid #eef2f7}.fx-spec{display:grid;grid-template-columns:230px 1fr;gap:16px;padding:12px 4px;border-bottom:1px solid #eef2f7}.fx-k{font-weight:700;color:#334155}.fx-v{color:#475569}.fx-docs{display:flex;flex-direction:column;gap:10px}.fx-doc{display:flex;justify-content:space-between;align-items:center;gap:12px;padding:12px 14px;border:1px solid #e5e7eb;border-radius:8px}.fx-doc a{color:#2563eb;font-weight:700;text-decoration:none}.fx-doc a:hover{text-decoration:underline}.fx-scroll{overflow-x:auto}.fx-table{border-collapse:collapse;width:100%;min-width:760px;font-size:13px}.fx-table th,.fx-table td{border:1px solid #e5e7eb;padding:8px 10px;text-align:left}.fx-table th{background:#f8fafc;font-weight:700}.fx-note{color:#64748b;font-size:13px;margin-top:12px}\n @media (max-width:749px){.fx-spec{grid-template-columns:1fr;gap:4px}.fx-tab{min-width:50%;flex:1 1 50%}.fx-panel{padding:16px}} \u003c\/style\u003e \u003cscript\u003e\n (function () {\n var roots = document.querySelectorAll('[data-fx-tabs]');\n roots.forEach(function (root) {\n var tabs = root.querySelectorAll('[data-fx-tab]');\n var panels = root.querySelectorAll('[data-fx-panel]');\n tabs.forEach(function (t) {\n t.addEventListener('click', function () {\n var i = t.getAttribute('data-fx-tab');\n tabs.forEach(function (x) { x.classList.toggle('is-active', x === t); });\n panels.forEach(function (p) { p.classList.toggle('is-active', p.getAttribute('data-fx-panel') === i); });\n });\n });\n });\n })(); \u003c\/script\u003e","brand":"Firefly","offers":[{"title":"4G RAM+32G ROM","offer_id":48422467993858,"sku":"firefly-aibox-186-artificial-intelligence-box-6t-large-model-privatization-deployment-deep-learning-computing-cv186ah-41690042105940","price":309.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0837\/5953\/0242\/files\/AIBox-186-800800_1_1_685e4017-fac5-4d3f-b0a7-09bfa2609cf6.jpg?v=1788244293"},{"product_id":"aibox-1688-large-modelal-box","title":"AIBOX-1688 AI Edge Computing Embedded PC","description":"\u003cp class=\"geo-summary\" style=\"font-size:1rem;line-height:1.65;margin:0 0 1.25rem;padding:0 0 1rem;border-bottom:1px solid #e5e7eb;color:#1f2937\"\u003e\u003cstrong\u003eAIBOX-1688 AI Edge Computing Embedded PC\u003c\/strong\u003e is a Firefly product sold by Ai-Paipai. Key specifications — Soc: SOPHON BM1688 · Ram: 8GB LPDDR4 (4GB\/8GB\/16GB optional) · Storage: 32GB eMMC (32GB\/64GB\/128GB\/256GB optional) · Ethernet: 2 x 1000Mbps Ethernet · Video output: 1 x HDMI2.0 (4K@60fps). Typical applications: edge AI inference, machine vision and industrial automation. Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.) is an authorized distributor providing local technical support, pre-installed SDK \/ OS images, OEM \/ ODM customization, and worldwide shipping.\u003c\/p\u003e \u003c!-- Firefly product tabs --\u003e \u003cdiv class=\"fx-tabs\" data-fx-tabs\u003e \u003cdiv class=\"fx-tablist\" role=\"tablist\"\u003e \u003cbutton class=\"fx-tab is-active\" role=\"tab\" data-fx-tab=\"0\"\u003eDescription\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"1\"\u003eWhat's Included\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"2\"\u003eSpecifications\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"3\"\u003eDocuments\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"4\"\u003eShipping Information\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"5\"\u003eWhy Buy From Ai-Paipai?\u003c\/button\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel is-active\" data-fx-panel=\"0\"\u003e \u003cdiv style=\"border:2px solid #2b6cb0;background:#f0f7ff;padding:14px 18px;margin:0 0 18px;border-radius:8px;\"\u003e \u003ch3 style=\"margin:0 0 6px;color:#2b6cb0;\"\u003e✅ Authorized Distributor — Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.)\u003c\/h3\u003e \u003cp style=\"margin:0;font-size:14px;\"\u003eThis product is supplied by an \u003cb\u003eauthorized distributor\u003c\/b\u003e of the original brand.\nWe provide \u003cb\u003elocal technical support, pre-installed SDK \/ mirror images, and OEM \/ ODM customization\u003c\/b\u003e, plus fast global shipping.\u003c\/p\u003e \u003c\/div\u003e \u003cp\u003eThe AIBOX-1688 AI edge computer delivers 16 TOPS of processing power, enabling private deployment of mainstream large AI models for secure, customized on-device intelligence in enterprise and industrial applications.\u003c\/p\u003e \u003cul\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-1688_AIBOX-186_Specification_EN.pdf?v=1752733724\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Wiki: \u003ca href=\"https:\/\/wiki.t-firefly.com\/en\/AIBOX-1688\/preface.html\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e \u003cul\u003e \u003cli\u003e \u003cstrong\u003e16 TOPS AI Processor BM1688: \u003c\/strong\u003eThe BM1688 AI processor by SOPHON features an octa-core ARM Cortex-A53 (up to 1.6GHz) and a TPU acceleration engine, delivering 32 TOPS INT4, 16 TOPS INT8, 4 TFLOPS FP16\/BF16, and 0.5 TFLOPS FP32 performance. Supporting major AI frameworks, it's ideal for AI inference, computer vision, and edge computing applications.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eMulti-channel Video AI Performance:\u003c\/strong\u003e The AI edge computing box delivers robust video processing with 16-channel 1080P H.264 decoding, 10-channel 1080P encoding, and simultaneous 16-channel HD video analysis.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eStrong Network Communication Capability:\u003c\/strong\u003e The AIBOX embedded PC is equipped with dual 1000Mbps Ethernet ports to ensure high-speed and stable network communication, meeting the needs of various application scenarios.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eAll-aluminum Alloy Enclosure:\u003c\/strong\u003e The industrial-grade AI box features a rugged all-metal enclosure with aluminum alloy construction for superior thermal conduction. Its optimized grille design enables efficient airflow and heat dissipation, maintaining peak computing performance and reliability even in high-temperature environments.\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eHardware Overview\u003c\/strong\u003e\u003c\/h2\u003e \u003cp\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-1688.webp?v=1752733594\"\u003e\u003c\/p\u003e \u003c!----\u003e\u003chr\u003e \u003ch2\u003e \u003c\/h2\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"1\"\u003e \u003ch3\u003eShipping list\u003c\/h3\u003e \u003cul\u003e \u003cli\u003eMain unit × 1\u003c\/li\u003e \u003cli\u003ePower adapter \/ cable (region plug on request) × 1\u003c\/li\u003e \u003cli\u003eAccessories vary by configuration — contact us for the exact included list.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"2\"\u003e \u003cdiv class=\"fx-specs\"\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSoc\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eSOPHON BM1688\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eCpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eOcta-core ARM Cortex-A53 @ 1.6GHz\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eTpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eBuilt-in SOPHGO neural network acceleration engine TPU, 32T@INT4 peak computing power, 16T@INT8 peak computing power, 4T@FP16\/BF16computing power, 0.5T@FP32 computing power\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eVpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eVideo decoding: H.264 \/ H.265 decoding (Max performance: 1920 * 1080@480FPS or 3840 * 2160 @120FPS)\nVideo encoding: H.264 \/ H.265 encoding (Max performance: 1920 * 1080@300FPS or 3840 * 2160 @75 FPS)\nImage codec: JPEG\/MJPEG Baseline codec (JPEG codec with a maximum resolution of 1080P@480 FPS)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eRam\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e8GB LPDDR4 (4GB\/8GB\/16GB optional)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eStorage\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e32GB eMMC (32GB\/64GB\/128GB\/256GB optional)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eStorage expansion\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 x M.2 (Expandable PCIe NVMe SSD(default support)\/SATA SSD(supported after software update), supports 2242\/2260\/2280) (inside the device), 1 x TF Card\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eDC 12V\/3A (DC 5.5 x 2.1mm)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower consumption\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eNormal: 7.2W(12V\/600mA)\nMax: 14.4W(12V\/1200mA)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eVideo output\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 x HDMI2.0 (4K@60fps)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eOs\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eLinux\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSoftware support\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eThe private deployment of ultra-large-scale parameter models under the Transformer architecture, including large language models such as Gemma-2B, LlaMa2-7B, ChatGLM3-6B, Qwen1.5-1.8B.\nTraditional network architectures such as CNN, RNN, and LSTM; a variety of deep learning frameworks, including TensorFlow, PyTorch, MXNet, PaddlePaddle, and ONNX, as well as custom operator development\nDocker container management technology\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eDimension\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e93.4 mm × 93.4 mm × 50 mm\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eWeight\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e≈ 500g\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEnvironment\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eOperating Temperature: -20℃~60℃\nStorage Temperature: -20℃~70℃\nStorage Humidity: 10%~90%RH (non-condensing)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEthernet\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 x 1000Mbps Ethernet\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eUsb\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 x USB3.0 (Current Limit: 1A)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eOther\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 x Type-C (USB 2.0 device mode only)\n1 x Console (Debug serial)\n1 x Power button\n1 x Recovery\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eProduct tutorials\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSdk software and firmware files\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"3\"\u003e \u003cdiv class=\"fx-docs\"\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct tutorials\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct datasheet\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eSDK software and firmware files\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eDocument links will be replaced with the official Firefly resource URLs on request.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"4\"\u003e \u003cp\u003e\u003cb\u003eOur cooperating carriers:\u003c\/b\u003e FedEx, DHL, UPS, SF Express\u003c\/p\u003e \u003ch3\u003eDelivery Area And Cost\u003c\/h3\u003e \u003cdiv class=\"fx-scroll\"\u003e \u003ctable class=\"fx-table\"\u003e \u003cthead\u003e\u003ctr\u003e \u003cth\u003eCountry\/Region\u003c\/th\u003e \u003cth\u003e0–2kg\u003c\/th\u003e \u003cth\u003e2–3kg\u003c\/th\u003e \u003cth\u003e3–4kg\u003c\/th\u003e \u003cth\u003e4–5kg\u003c\/th\u003e \u003cth\u003e5–6kg\u003c\/th\u003e \u003cth\u003e6–7kg\u003c\/th\u003e \u003cth\u003e7–8kg\u003c\/th\u003e \u003cth\u003e8–9kg\u003c\/th\u003e \u003cth\u003e9–10kg\u003c\/th\u003e \u003c\/tr\u003e\u003c\/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd\u003eJapan, Taiwan, Hong Kong, Macau\u003c\/td\u003e \u003ctd\u003e$15\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSingapore, Thailand, Malaysia\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eIndonesia, Philippines\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003ctd\u003e$70\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSouth Korea\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eUnited States, Australia, New Zealand, Canada, UK, and most of Western Europe\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$75\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$105\u003c\/td\u003e \u003ctd\u003e$115\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eOther regions (Eastern Europe, Middle East, Latin America, etc.)\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$110\u003c\/td\u003e \u003ctd\u003e$125\u003c\/td\u003e \u003ctd\u003e$135\u003c\/td\u003e \u003ctd\u003e$150\u003c\/td\u003e \u003ctd\u003e$165\u003c\/td\u003e \u003c\/tr\u003e \u003c\/tbody\u003e \u003c\/table\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eShipping time is for reference only; the actual situation shall prevail.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"5\"\u003e\n Why Buy From Ai-Paipai? \u003cul\u003e \u003cli\u003e \u003cb\u003eAuthorized \u0026amp; Genuine\u003c\/b\u003e — sourced directly from brand-approved channels.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eLocal Engineering Support\u003c\/b\u003e — datasheets, SDKs, and pre-flashed images in English and Chinese.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOEM \/ ODM \u0026amp; FPGA Customization\u003c\/b\u003e — tailor specs, enclosures, and BSP for your project.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOne-Stop Sourcing\u003c\/b\u003e — Firefly + youyeetoo + our own FPGA \/ edge lineup in one store.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cstyle\u003e.fx-tabs{margin:24px 0;border:1px solid #e5e7eb;border-radius:10px;overflow:hidden;background:#fff}.fx-tablist{display:flex;flex-wrap:wrap;gap:0;border-bottom:1px solid #e5e7eb;background:#f8fafc}.fx-tab{flex:1 1 auto;min-width:120px;padding:14px 16px;border:0;background:transparent;cursor:pointer;font:600 14px\/1.3 inherit;color:#475569;border-bottom:3px solid transparent;transition:.18s}.fx-tab:hover{color:#0f172a;background:#eef2f7}.fx-tab.is-active{color:#0f172a;border-bottom-color:#2563eb;background:#fff}.fx-panel{display:none;padding:22px 24px}.fx-panel.is-active{display:block}.fx-panel h3{font-size:16px;margin:22px 0 8px;font-weight:700}.fx-panel h3:first-child{margin-top:0}.fx-panel p{margin:10px 0;line-height:1.65}.fx-panel ul{margin:10px 0;padding-left:22px}.fx-panel li{margin:6px 0;line-height:1.6}.fx-auth{background:#f0fdf4;border:1px solid #bbf7d0;border-radius:8px;padding:12px 14px;margin:0 0 16px;font-size:14px;line-height:1.6}.fx-specs{border-top:1px solid #eef2f7}.fx-spec{display:grid;grid-template-columns:230px 1fr;gap:16px;padding:12px 4px;border-bottom:1px solid #eef2f7}.fx-k{font-weight:700;color:#334155}.fx-v{color:#475569}.fx-docs{display:flex;flex-direction:column;gap:10px}.fx-doc{display:flex;justify-content:space-between;align-items:center;gap:12px;padding:12px 14px;border:1px solid #e5e7eb;border-radius:8px}.fx-doc a{color:#2563eb;font-weight:700;text-decoration:none}.fx-doc a:hover{text-decoration:underline}.fx-scroll{overflow-x:auto}.fx-table{border-collapse:collapse;width:100%;min-width:760px;font-size:13px}.fx-table th,.fx-table td{border:1px solid #e5e7eb;padding:8px 10px;text-align:left}.fx-table th{background:#f8fafc;font-weight:700}.fx-note{color:#64748b;font-size:13px;margin-top:12px}\n @media (max-width:749px){.fx-spec{grid-template-columns:1fr;gap:4px}.fx-tab{min-width:50%;flex:1 1 50%}.fx-panel{padding:16px}} \u003c\/style\u003e \u003cscript\u003e\n (function () {\n var roots = document.querySelectorAll('[data-fx-tabs]');\n roots.forEach(function (root) {\n var tabs = root.querySelectorAll('[data-fx-tab]');\n var panels = root.querySelectorAll('[data-fx-panel]');\n tabs.forEach(function (t) {\n t.addEventListener('click', function () {\n var i = t.getAttribute('data-fx-tab');\n tabs.forEach(function (x) { x.classList.toggle('is-active', x === t); });\n panels.forEach(function (p) { p.classList.toggle('is-active', p.getAttribute('data-fx-panel') === i); });\n });\n });\n });\n })(); \u003c\/script\u003e","brand":"Firefly","offers":[{"title":"8G RAM+32G ROM","offer_id":48422468223234,"sku":"firefly-aibox-1688-large-modelal-box-42727547174996","price":409.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+64G ROM","offer_id":48422468256002,"sku":"firefly-aibox-1688-large-modelal-box-42761625108564","price":419.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0837\/5953\/0242\/files\/AIBox-1688-800800_1_bb951a0c-7b07-4d97-855e-769de7bcb014.jpg?v=1788244297"},{"product_id":"aibox-8550-qcs8550-embedded-mini-pc","title":"AIBOX-8550 QCS8550 Embedded Mini PC","description":"\u003cp class=\"geo-summary\" style=\"font-size:1rem;line-height:1.65;margin:0 0 1.25rem;padding:0 0 1rem;border-bottom:1px solid #e5e7eb;color:#1f2937\"\u003e\u003cstrong\u003eAIBOX-8550 QCS8550 Embedded Mini PC\u003c\/strong\u003e is a Firefly product sold by Ai-Paipai. Key specifications — Soc: Qualcomm QCS8550 · Npu: Dual eNPU V3: Equipped with 4 HVX (Hexagon Vector… · Ram: 16GB LPDDR5x · Storage: 256GB UFS4.0 · Ethernet: 2 × Gigabit Ethernet (1000Mbps\/RJ45). Typical applications: edge AI inference and industrial automation. Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.) is an authorized distributor providing local technical support, pre-installed SDK \/ OS images, OEM \/ ODM customization, and worldwide shipping.\u003c\/p\u003e \u003c!-- Firefly product tabs --\u003e \u003cdiv class=\"fx-tabs\" data-fx-tabs\u003e \u003cdiv class=\"fx-tablist\" role=\"tablist\"\u003e \u003cbutton class=\"fx-tab is-active\" role=\"tab\" data-fx-tab=\"0\"\u003eDescription\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"1\"\u003eWhat's Included\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"2\"\u003eSpecifications\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"3\"\u003eDocuments\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"4\"\u003eShipping Information\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"5\"\u003eWhy Buy From Ai-Paipai?\u003c\/button\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel is-active\" data-fx-panel=\"0\"\u003e \u003cdiv style=\"border:2px solid #2b6cb0;background:#f0f7ff;padding:14px 18px;margin:0 0 18px;border-radius:8px;\"\u003e \u003ch3 style=\"margin:0 0 6px;color:#2b6cb0;\"\u003e✅ Authorized Distributor — Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.)\u003c\/h3\u003e \u003cp style=\"margin:0;font-size:14px;\"\u003eThis product is supplied by an \u003cb\u003eauthorized distributor\u003c\/b\u003e of the original brand.\nWe provide \u003cb\u003elocal technical support, pre-installed SDK \/ mirror images, and OEM \/ ODM customization\u003c\/b\u003e, plus fast global shipping.\u003c\/p\u003e \u003c\/div\u003e \u003cp\u003eThe AIBOX-8550 is equipped with a Qualcomm QCS8550 octa-core AI processor, integrating a 48 TOPS NPU, supporting mainstream AI large language models and deep learning frameworks. It features a built-in Adreno 740 GPU, supporting ray tracing and 8K video codecs. Utilizing an industrial-grade all-metal casing, it offers efficient heat dissipation, ensuring stable operation around the clock and meeting the demands of demanding industrial applications.\u003c\/p\u003e \u003cul\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/download.t-firefly.com\/Spec\/Computers\/AIBOX-8550_Specification_EN.pdf\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 23px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e \u003cul\u003e \u003cli\u003e \u003cstrong\u003eHigh-Performance Processor Qualcomm QCS8550:\u003c\/strong\u003e The QCS8550 features an eight-core Kryo CPU based on the ARM architecture, with a clock speed of up to 3.36 GHz, providing powerful support for high-performance computing and multitasking.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eDeployment of Large AI Models: \u003c\/strong\u003eSupports the private deployment of large-scale Transformer models (including Qwen, Llama, Gemma, DeepSeek-R1, and Phi series), as well as mainstream deep learning frameworks such as TensorFlow, PyTorch, Caffe, and ONNX.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eSupports Ray Tracing Technology:\u003c\/strong\u003e Features an Adreno 740 GPU, providing full ray tracing support and compatibility with OpenGL ES 3.2, Vulkan 1.2, and OpenCL 3.0. Combined with Adreno Neural Processing technology, it significantly enhances graphics and AI computing performance.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003e8K Video Encoding and Decoding:\u003c\/strong\u003e Advanced video processing supporting 8K@60fps\/4K@240fps decoding and 8K@30fps\/4K@120fps encoding.\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 23px;\"\u003e\u003cstrong\u003eProduct Overview\u003c\/strong\u003e\u003c\/h2\u003e \u003cp\u003e\u003cstrong\u003e\u003cimg style=\"display: block; margin-left: auto; margin-right: auto;\" alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/ScreenShot_2025-12-03_162506_694.webp?v=1764750475\"\u003e\u003c\/strong\u003e\u003c\/p\u003e \u003chr\u003e \u003ch2\u003e \u003c\/h2\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"1\"\u003e \u003ch3\u003eShipping list\u003c\/h3\u003e \u003cul\u003e \u003cli\u003eMain unit × 1\u003c\/li\u003e \u003cli\u003ePower adapter \/ cable (region plug on request) × 1\u003c\/li\u003e \u003cli\u003eAccessories vary by configuration — contact us for the exact included list.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"2\"\u003e \u003cdiv class=\"fx-specs\"\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSoc\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eQualcomm QCS8550\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eCpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eQualcomm Kryo® CPU: Octa-core 64-bit (1×GoldPlus@3.2GHz + (2+2)Gold@2.8GHz + 3×Silver@2.0GHz), 4nm advanced process, maximum frequency up to 3.36GHz\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eGpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eAdreno 740 GPU: Supports ray tracing technology, OpenGL ES 3.2, Vulkan 1.2, full-profile OpenCL 3.0, and Adreno NN Direct\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eNpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eDual eNPU V3: Equipped with 4 HVX (Hexagon Vector Extensions), 1 HMX (Hexagon Matrix Extension); Computing power up to 48 TOPS (INT8), 12 TOPS (FP16)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eRam\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e16GB LPDDR5x\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eStorage\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e256GB UFS4.0\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eDC 12V\/5A (5.5 × 2.1mm)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower consumption\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eNormal: 4.32W(12V\/360mA), Max: 20W(12V\/1670mA), Min(Sleep): 0.6W(12V\/50mA)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eOs\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eUbubtu\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSoftware support\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eSupports on-premises deployment of large-scale parameter models based on the Transformer architecture, such as large language models (LLMs) including the Deepseek-R1 series, Gemma series, Llama series, Qwen series, Phi series, etc.\nSupports the QNN AI inference framework, as well as various deep learning frameworks including TensorFlow, TensorFlow Lite, PyTorch, ONNX, etc.\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eDimension\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e93.4mm × 93.4mm × 50.0mm\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eWeight\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e≈ 500g\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEnvironment\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eOperating Temperature: -20℃~60℃, Storage Temperature: -20℃~70℃, Operating Humidity: 10%~90%RH (No condensation)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEthernet\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 × Gigabit Ethernet (1000Mbps\/RJ45)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eUsb\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 × USB3.0 (Max: 1A), 1 × Type-C (For download)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eButton\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 × Power, 1 × Recovery\u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"3\"\u003e \u003cdiv class=\"fx-docs\"\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct tutorials\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct datasheet\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eSDK software and firmware files\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eDocument links will be replaced with the official Firefly resource URLs on request.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"4\"\u003e \u003cp\u003e\u003cb\u003eOur cooperating carriers:\u003c\/b\u003e FedEx, DHL, UPS, SF Express\u003c\/p\u003e \u003ch3\u003eDelivery Area And Cost\u003c\/h3\u003e \u003cdiv class=\"fx-scroll\"\u003e \u003ctable class=\"fx-table\"\u003e \u003cthead\u003e\u003ctr\u003e \u003cth\u003eCountry\/Region\u003c\/th\u003e \u003cth\u003e0–2kg\u003c\/th\u003e \u003cth\u003e2–3kg\u003c\/th\u003e \u003cth\u003e3–4kg\u003c\/th\u003e \u003cth\u003e4–5kg\u003c\/th\u003e \u003cth\u003e5–6kg\u003c\/th\u003e \u003cth\u003e6–7kg\u003c\/th\u003e \u003cth\u003e7–8kg\u003c\/th\u003e \u003cth\u003e8–9kg\u003c\/th\u003e \u003cth\u003e9–10kg\u003c\/th\u003e \u003c\/tr\u003e\u003c\/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd\u003eJapan, Taiwan, Hong Kong, Macau\u003c\/td\u003e \u003ctd\u003e$15\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSingapore, Thailand, Malaysia\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eIndonesia, Philippines\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003ctd\u003e$70\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSouth Korea\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eUnited States, Australia, New Zealand, Canada, UK, and most of Western Europe\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$75\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$105\u003c\/td\u003e \u003ctd\u003e$115\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eOther regions (Eastern Europe, Middle East, Latin America, etc.)\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$110\u003c\/td\u003e \u003ctd\u003e$125\u003c\/td\u003e \u003ctd\u003e$135\u003c\/td\u003e \u003ctd\u003e$150\u003c\/td\u003e \u003ctd\u003e$165\u003c\/td\u003e \u003c\/tr\u003e \u003c\/tbody\u003e \u003c\/table\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eShipping time is for reference only; the actual situation shall prevail.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"5\"\u003e\n Why Buy From Ai-Paipai? \u003cul\u003e \u003cli\u003e \u003cb\u003eAuthorized \u0026amp; Genuine\u003c\/b\u003e — sourced directly from brand-approved channels.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eLocal Engineering Support\u003c\/b\u003e — datasheets, SDKs, and pre-flashed images in English and Chinese.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOEM \/ ODM \u0026amp; FPGA Customization\u003c\/b\u003e — tailor specs, enclosures, and BSP for your project.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOne-Stop Sourcing\u003c\/b\u003e — Firefly + youyeetoo + our own FPGA \/ edge lineup in one store.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cstyle\u003e.fx-tabs{margin:24px 0;border:1px solid #e5e7eb;border-radius:10px;overflow:hidden;background:#fff}.fx-tablist{display:flex;flex-wrap:wrap;gap:0;border-bottom:1px solid #e5e7eb;background:#f8fafc}.fx-tab{flex:1 1 auto;min-width:120px;padding:14px 16px;border:0;background:transparent;cursor:pointer;font:600 14px\/1.3 inherit;color:#475569;border-bottom:3px solid transparent;transition:.18s}.fx-tab:hover{color:#0f172a;background:#eef2f7}.fx-tab.is-active{color:#0f172a;border-bottom-color:#2563eb;background:#fff}.fx-panel{display:none;padding:22px 24px}.fx-panel.is-active{display:block}.fx-panel h3{font-size:16px;margin:22px 0 8px;font-weight:700}.fx-panel h3:first-child{margin-top:0}.fx-panel p{margin:10px 0;line-height:1.65}.fx-panel ul{margin:10px 0;padding-left:22px}.fx-panel li{margin:6px 0;line-height:1.6}.fx-auth{background:#f0fdf4;border:1px solid #bbf7d0;border-radius:8px;padding:12px 14px;margin:0 0 16px;font-size:14px;line-height:1.6}.fx-specs{border-top:1px solid #eef2f7}.fx-spec{display:grid;grid-template-columns:230px 1fr;gap:16px;padding:12px 4px;border-bottom:1px solid #eef2f7}.fx-k{font-weight:700;color:#334155}.fx-v{color:#475569}.fx-docs{display:flex;flex-direction:column;gap:10px}.fx-doc{display:flex;justify-content:space-between;align-items:center;gap:12px;padding:12px 14px;border:1px solid #e5e7eb;border-radius:8px}.fx-doc a{color:#2563eb;font-weight:700;text-decoration:none}.fx-doc a:hover{text-decoration:underline}.fx-scroll{overflow-x:auto}.fx-table{border-collapse:collapse;width:100%;min-width:760px;font-size:13px}.fx-table th,.fx-table td{border:1px solid #e5e7eb;padding:8px 10px;text-align:left}.fx-table th{background:#f8fafc;font-weight:700}.fx-note{color:#64748b;font-size:13px;margin-top:12px}\n @media (max-width:749px){.fx-spec{grid-template-columns:1fr;gap:4px}.fx-tab{min-width:50%;flex:1 1 50%}.fx-panel{padding:16px}} \u003c\/style\u003e \u003cscript\u003e\n (function () {\n var roots = document.querySelectorAll('[data-fx-tabs]');\n roots.forEach(function (root) {\n var tabs = root.querySelectorAll('[data-fx-tab]');\n var panels = root.querySelectorAll('[data-fx-panel]');\n tabs.forEach(function (t) {\n t.addEventListener('click', function () {\n var i = t.getAttribute('data-fx-tab');\n tabs.forEach(function (x) { x.classList.toggle('is-active', x === t); });\n panels.forEach(function (p) { p.classList.toggle('is-active', p.getAttribute('data-fx-panel') === i); });\n });\n });\n });\n })(); \u003c\/script\u003e","brand":"Firefly","offers":[{"title":"16G RAM+256G ROM","offer_id":48422469173506,"sku":"firefly-aibox-8550-qcs8550-embedded-mini-pc-42730903175252","price":799.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0837\/5953\/0242\/files\/8550_3e3a0150-8847-4590-aacf-9bf14ff58084.webp?v=1788244310"},{"product_id":"aibox-3588s-embedded-fanless-pc","title":"AIBOX-3588S RK3588S Embedded Fanless PC","description":"\u003cp class=\"geo-summary\" style=\"font-size:1rem;line-height:1.65;margin:0 0 1.25rem;padding:0 0 1rem;border-bottom:1px solid #e5e7eb;color:#1f2937\"\u003e\u003cstrong\u003eAIBOX-3588S RK3588S Embedded Fanless PC\u003c\/strong\u003e is a Firefly product sold by Ai-Paipai. Key specifications — Soc: Rockchip RK3588S · Npu: 6 TOPS NPU, supports INT4\/INT8\/INT16 mixed operations · Ram: LPDDR5 (4GB\/8GB\/16GB\/32GB optional) · Storage: eMMC (16GB\/32GB\/64GB\/128GB\/256GB optional) · Ethernet: 2 x Gigabit Ethernet (1000Mbps\/RJ45). Typical applications: edge AI inference, industrial automation and digital signage and HMI. Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.) is an authorized distributor providing local technical support, pre-installed SDK \/ OS images, OEM \/ ODM customization, and worldwide shipping.\u003c\/p\u003e \u003c!-- Firefly product tabs --\u003e \u003cdiv class=\"fx-tabs\" data-fx-tabs\u003e \u003cdiv class=\"fx-tablist\" role=\"tablist\"\u003e \u003cbutton class=\"fx-tab is-active\" role=\"tab\" data-fx-tab=\"0\"\u003eDescription\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"1\"\u003eWhat's Included\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"2\"\u003eSpecifications\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"3\"\u003eDocuments\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"4\"\u003eShipping Information\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"5\"\u003eWhy Buy From Ai-Paipai?\u003c\/button\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel is-active\" data-fx-panel=\"0\"\u003e \u003cdiv style=\"border:2px solid #2b6cb0;background:#f0f7ff;padding:14px 18px;margin:0 0 18px;border-radius:8px;\"\u003e \u003ch3 style=\"margin:0 0 6px;color:#2b6cb0;\"\u003e✅ Authorized Distributor — Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.)\u003c\/h3\u003e \u003cp style=\"margin:0;font-size:14px;\"\u003eThis product is supplied by an \u003cb\u003eauthorized distributor\u003c\/b\u003e of the original brand.\nWe provide \u003cb\u003elocal technical support, pre-installed SDK \/ mirror images, and OEM \/ ODM customization\u003c\/b\u003e, plus fast global shipping.\u003c\/p\u003e \u003c\/div\u003e \u003cp\u003eAIBOX-3588 low-power large-model embedded PC supports mainstream large-model private deployment, privatizing AI computing power, and one box can meet personalized AI deployment! The host features a built-in ARM Mali-G610 MP4 quad-core GPU, offering computing power of up to 6 TOPS. This enables more intelligent data processing, voice recognition, and image analysis, meeting the edge computing AI application needs of most terminal devices.\u003c\/p\u003e \u003cul\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/download.t-firefly.com\/Spec\/Computers\/AIBOX-3576_AIBOX-3588_AIBOX-3588S_Specification_EN.pdf\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Wiki: \u003ca href=\"https:\/\/wiki.t-firefly.com\/en\/AIBOX-3588S\/index.html\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e \u003cul\u003e \u003cli\u003e \u003cstrong\u003eOcta-core AIOT Processor RK3588S:\u003c\/strong\u003e RK3588S is Rockchip's flagship AIoT chip, built with advanced 8nm LP process technology. It is equipped with an octa-core 64-bit CPU with a main frequency of up to 2.4GHz, an integrated ARM Mali-G610 MP4 quad-core GPU, and a built-in AI accelerator NPU, which can provide 6 TOPS computing power. RK3588S is performance optimized for various AI applications.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003ePrivate Deployment of Large AI Models:\u003c\/strong\u003e RK3588S has 6 TOPS NPU computing power and supports large-scale private deployment of Transformer-based models, including large language models (LLMs) such as the Gemma series, ChatGLM series, Qwen series, and Phi series. It also supports RKNN model import and export and supports multiple deep learning frameworks such as TensorFlow, TensorFlow Lite, PyTorch, and Caffe.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003e32GB LPDDR5 High-Capacity Memory:\u003c\/strong\u003e LPDDR5 outperforms LPDDR4 with greater capacity, higher bandwidth, faster speeds, lower power use, and advanced ECC, meeting large model deployment needs for memory and responsiveness to boost performance and energy efficiency.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003e8K Video Encoding \u0026amp; Decoding: \u003c\/strong\u003eIt supports 8K@60fps VP9 decoding and 8K@30fps H.264 encoding, and has simultaneous encoding and decoding capabilities. It can handle up to 32 channels of 1080P@30fps decoding and 16 channels of 1080P@30fps encoding.\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eHardware Overview\u003c\/strong\u003e\u003c\/h2\u003e \u003cdiv style=\"text-align: left;\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/ScreenShot_2025-10-21_170631_979.webp?v=1761037757\" alt=\"aibox-3588s mini pc\" style=\"float: none;\"\u003e\u003c\/div\u003e \u003chr\u003e \u003ch2\u003e \u003c\/h2\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"1\"\u003e \u003ch3\u003eShipping list\u003c\/h3\u003e \u003cul\u003e \u003cli\u003eMain unit × 1\u003c\/li\u003e \u003cli\u003ePower adapter \/ cable (region plug on request) × 1\u003c\/li\u003e \u003cli\u003eAccessories vary by configuration — contact us for the exact included list.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"2\"\u003e \u003cdiv class=\"fx-specs\"\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSoc\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eRockchip RK3588S\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eCpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eOcta-core 64-bit processor(4×Cortex-A76+4×Cortex-A55), main frequency up to 2.4 GHz\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eGpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eARM Mali-G610 MP4 quad-core GPU, supports OpenGL ES3.2\/OpenCL 2.2\/Vulkan1.1, 450 GFLOPS\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eNpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e6 TOPS NPU, supports INT4\/INT8\/INT16 mixed operations\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eVpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eDecode: \n8K@60fps VP9\/AVS2\n8K@30fps H.264 AVC\/MVC\n4K@60fps AV1\n1080P@60fps MPEG-2\/-1\/VC-1\/VP8\nEncode: \n8K@30fps H.264\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eRam\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eLPDDR5 (4GB\/8GB\/16GB\/32GB optional)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eStorage\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eeMMC (16GB\/32GB\/64GB\/128GB\/256GB optional)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eDC 12V\/2A (DC 5.5 × 2.1 mm)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower consumption\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eNormal: 1.26W(12V\/105mA)\nMax: 13.2W(12V\/1100mA)\nMin(Sleep): 0.18W(12V\/15mA)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eVideo output\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 x HDMI2.1 (8K@60fps)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eOs\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eLinux\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSoftware support\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eSupport the deployment of ultra-large-scale parametric models under the Transformer architecture, such as the Gemma series, ChatGLM series, Qwen series, and Phi series, as well as other large language models.\nIt supports traditional network architectures such as CNN, RNN, and LSTM, and supports the import and export of RKNN models; supports a variety of deep learning frameworks, including TensorFlow, TensorFlow Lite, PyTorch, Caffe, ONNX, and Darknet. It also supports the development of custom operators.\nSupport Docker container management technology.\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eWeight\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e0.5 kg\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEnvironment\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eOperating: -20℃~60℃\nStorage: -20℃~70℃\nStorage Humidity: 10%~90%RH (non-condensing)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEthernet\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 x Gigabit Ethernet (1000Mbps\/RJ45)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eUsb\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 × USB 3.0 (Max: 1A), 1 × Type-C (Can be used as a firmware flashing port)\nSet to USB2.0 HOST after booting up)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eButton\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 x Power, 1 x MaskRom\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eOther\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 x Console (Debug serial)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eProduct tutorials\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSdk software and firmware files\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"3\"\u003e \u003cdiv class=\"fx-docs\"\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct tutorials\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct datasheet\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eSDK software and firmware files\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eDocument links will be replaced with the official Firefly resource URLs on request.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"4\"\u003e \u003cp\u003e\u003cb\u003eOur cooperating carriers:\u003c\/b\u003e FedEx, DHL, UPS, SF Express\u003c\/p\u003e \u003ch3\u003eDelivery Area And Cost\u003c\/h3\u003e \u003cdiv class=\"fx-scroll\"\u003e \u003ctable class=\"fx-table\"\u003e \u003cthead\u003e\u003ctr\u003e \u003cth\u003eCountry\/Region\u003c\/th\u003e \u003cth\u003e0–2kg\u003c\/th\u003e \u003cth\u003e2–3kg\u003c\/th\u003e \u003cth\u003e3–4kg\u003c\/th\u003e \u003cth\u003e4–5kg\u003c\/th\u003e \u003cth\u003e5–6kg\u003c\/th\u003e \u003cth\u003e6–7kg\u003c\/th\u003e \u003cth\u003e7–8kg\u003c\/th\u003e \u003cth\u003e8–9kg\u003c\/th\u003e \u003cth\u003e9–10kg\u003c\/th\u003e \u003c\/tr\u003e\u003c\/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd\u003eJapan, Taiwan, Hong Kong, Macau\u003c\/td\u003e \u003ctd\u003e$15\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSingapore, Thailand, Malaysia\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eIndonesia, Philippines\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003ctd\u003e$70\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSouth Korea\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eUnited States, Australia, New Zealand, Canada, UK, and most of Western Europe\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$75\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$105\u003c\/td\u003e \u003ctd\u003e$115\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eOther regions (Eastern Europe, Middle East, Latin America, etc.)\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$110\u003c\/td\u003e \u003ctd\u003e$125\u003c\/td\u003e \u003ctd\u003e$135\u003c\/td\u003e \u003ctd\u003e$150\u003c\/td\u003e \u003ctd\u003e$165\u003c\/td\u003e \u003c\/tr\u003e \u003c\/tbody\u003e \u003c\/table\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eShipping time is for reference only; the actual situation shall prevail.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"5\"\u003e\n Why Buy From Ai-Paipai? \u003cul\u003e \u003cli\u003e \u003cb\u003eAuthorized \u0026amp; Genuine\u003c\/b\u003e — sourced directly from brand-approved channels.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eLocal Engineering Support\u003c\/b\u003e — datasheets, SDKs, and pre-flashed images in English and Chinese.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOEM \/ ODM \u0026amp; FPGA Customization\u003c\/b\u003e — tailor specs, enclosures, and BSP for your project.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOne-Stop Sourcing\u003c\/b\u003e — Firefly + youyeetoo + our own FPGA \/ edge lineup in one store.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cstyle\u003e.fx-tabs{margin:24px 0;border:1px solid #e5e7eb;border-radius:10px;overflow:hidden;background:#fff}.fx-tablist{display:flex;flex-wrap:wrap;gap:0;border-bottom:1px solid #e5e7eb;background:#f8fafc}.fx-tab{flex:1 1 auto;min-width:120px;padding:14px 16px;border:0;background:transparent;cursor:pointer;font:600 14px\/1.3 inherit;color:#475569;border-bottom:3px solid transparent;transition:.18s}.fx-tab:hover{color:#0f172a;background:#eef2f7}.fx-tab.is-active{color:#0f172a;border-bottom-color:#2563eb;background:#fff}.fx-panel{display:none;padding:22px 24px}.fx-panel.is-active{display:block}.fx-panel h3{font-size:16px;margin:22px 0 8px;font-weight:700}.fx-panel h3:first-child{margin-top:0}.fx-panel p{margin:10px 0;line-height:1.65}.fx-panel ul{margin:10px 0;padding-left:22px}.fx-panel li{margin:6px 0;line-height:1.6}.fx-auth{background:#f0fdf4;border:1px solid #bbf7d0;border-radius:8px;padding:12px 14px;margin:0 0 16px;font-size:14px;line-height:1.6}.fx-specs{border-top:1px solid #eef2f7}.fx-spec{display:grid;grid-template-columns:230px 1fr;gap:16px;padding:12px 4px;border-bottom:1px solid #eef2f7}.fx-k{font-weight:700;color:#334155}.fx-v{color:#475569}.fx-docs{display:flex;flex-direction:column;gap:10px}.fx-doc{display:flex;justify-content:space-between;align-items:center;gap:12px;padding:12px 14px;border:1px solid #e5e7eb;border-radius:8px}.fx-doc a{color:#2563eb;font-weight:700;text-decoration:none}.fx-doc a:hover{text-decoration:underline}.fx-scroll{overflow-x:auto}.fx-table{border-collapse:collapse;width:100%;min-width:760px;font-size:13px}.fx-table th,.fx-table td{border:1px solid #e5e7eb;padding:8px 10px;text-align:left}.fx-table th{background:#f8fafc;font-weight:700}.fx-note{color:#64748b;font-size:13px;margin-top:12px}\n @media (max-width:749px){.fx-spec{grid-template-columns:1fr;gap:4px}.fx-tab{min-width:50%;flex:1 1 50%}.fx-panel{padding:16px}} \u003c\/style\u003e \u003cscript\u003e\n (function () {\n var roots = document.querySelectorAll('[data-fx-tabs]');\n roots.forEach(function (root) {\n var tabs = root.querySelectorAll('[data-fx-tab]');\n var panels = root.querySelectorAll('[data-fx-panel]');\n tabs.forEach(function (t) {\n t.addEventListener('click', function () {\n var i = t.getAttribute('data-fx-tab');\n tabs.forEach(function (x) { x.classList.toggle('is-active', x === t); });\n panels.forEach(function (p) { p.classList.toggle('is-active', p.getAttribute('data-fx-panel') === i); });\n });\n });\n });\n })(); \u003c\/script\u003e","brand":"Firefly","offers":[{"title":"8G RAM + 64G ROM","offer_id":48422470418690,"sku":"firefly-aibox-3588s-embedded-fanless-pc-42219978063956","price":499.0,"currency_code":"USD","in_stock":true},{"title":"16G RAM + 32G ROM","offer_id":48422470451458,"sku":"firefly-aibox-3588s-embedded-fanless-pc-42219978096724","price":779.0,"currency_code":"USD","in_stock":true},{"title":"32G RAM + 32G ROM","offer_id":48422470484226,"sku":"firefly-aibox-3588s-embedded-fanless-pc-42219978162260","price":1119.0,"currency_code":"USD","in_stock":true},{"title":"16G RAM+256G ROM","offer_id":48422470516994,"sku":"firefly-aibox-3588s-embedded-fanless-pc-42787214360660","price":839.0,"currency_code":"USD","in_stock":true},{"title":"32G RAM+256G ROM","offer_id":48422470549762,"sku":"firefly-aibox-3588s-embedded-fanless-pc-42893828522068","price":1209.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0837\/5953\/0242\/files\/AIBox-3588-800800_2_8249cf46-e64a-4292-b810-323dfd1a95d0.jpg?v=1788244324"},{"product_id":"aibox-1684x-ai-box-up-to-32-tops-of-computing-power","title":"AIBOX-1684X Embedded PC Edge Computing Video Analysis","description":"\u003cp class=\"geo-summary\" style=\"font-size:1rem;line-height:1.65;margin:0 0 1.25rem;padding:0 0 1rem;border-bottom:1px solid #e5e7eb;color:#1f2937\"\u003e\u003cstrong\u003eAIBOX-1684X Embedded PC Edge Computing Video Analysis\u003c\/strong\u003e is a Firefly product sold by Ai-Paipai. Key specifications — Soc: SOPHON BM1684X · Ram: 8GB\/12GB\/16GB LPDDR4\/LPDDR4X · Storage: 32GB\/64GB\/128GB eMMC, 1 × TF Card · Ethernet: 2 × Gigabit Ethernet (1000Mbps\/RJ45) · Software support: The private deployment of ultra-large-scale parameter…. Typical applications: edge AI inference, machine vision and industrial automation. Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.) is an authorized distributor providing local technical support, pre-installed SDK \/ OS images, OEM \/ ODM customization, and worldwide shipping.\u003c\/p\u003e \u003c!-- Firefly product tabs --\u003e \u003cdiv class=\"fx-tabs\" data-fx-tabs\u003e \u003cdiv class=\"fx-tablist\" role=\"tablist\"\u003e \u003cbutton class=\"fx-tab is-active\" role=\"tab\" data-fx-tab=\"0\"\u003eDescription\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"1\"\u003eWhat's Included\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"2\"\u003eSpecifications\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"3\"\u003eDocuments\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"4\"\u003eShipping Information\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"5\"\u003eWhy Buy From Ai-Paipai?\u003c\/button\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel is-active\" data-fx-panel=\"0\"\u003e \u003cdiv style=\"border:2px solid #2b6cb0;background:#f0f7ff;padding:14px 18px;margin:0 0 18px;border-radius:8px;\"\u003e \u003ch3 style=\"margin:0 0 6px;color:#2b6cb0;\"\u003e✅ Authorized Distributor — Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.)\u003c\/h3\u003e \u003cp style=\"margin:0;font-size:14px;\"\u003eThis product is supplied by an \u003cb\u003eauthorized distributor\u003c\/b\u003e of the original brand.\nWe provide \u003cb\u003elocal technical support, pre-installed SDK \/ mirror images, and OEM \/ ODM customization\u003c\/b\u003e, plus fast global shipping.\u003c\/p\u003e \u003c\/div\u003e \u003cp\u003e\u003ca href=\"https:\/\/www.firefly.store\/blogs\/news\/putting-a-large-language-model-into-a-small-box-aibox-1684x-embedded-pc\"\u003eDiscover AIBOX-1684X\u003c\/a\u003e\u003c\/p\u003e \u003cp\u003eAIBOX-1684X adopts SOPHON AI processor BM1684X, which can be configured with 16GB large memory and 128GB eMMC; supports 32TOPS (INT8) peak computing power, 16TFLOPS (FP16\/BF16) computing power, and 2TFLOPS (FP32) high-precision computing power; supports 32-channel H.265\/H.264 1080p@25fps video decoding; supports mainstream programming frameworks, has a complete tool chain and high ease of use, and low algorithm migration cost; suitable for a variety of AI computing scenarios such as visual computing, edge computing, general computing services, smart transportation, unmanned supermarkets, drones, etc.\u003c\/p\u003e \u003cul\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-1684X_AIBOX-1684_Specification_EN.pdf?v=1752722974\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Wiki: \u003ca href=\"https:\/\/wiki.t-firefly.com\/en\/AIBOX-1684X\/index.html\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e \u003cul\u003e \u003cli\u003e \u003cstrong\u003eThe Private Deployment of Large Models:\u003c\/strong\u003e Large language Models; Traditional network architectures; Docker container\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003e32TOPS BM1684X AI Processor: \u003c\/strong\u003eThe SOPHON AI processor BM1684X uses an octa-core ARM Cortex-A53 with a main frequency of up to 2.3GHz and adopts a 12nm lithography process.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003ePowerful Multi-channel Video AI Performance: \u003c\/strong\u003eThe embedded PC supports up to 32-channel 1080P H.264\/H.265 video decoding and 32-channel 1080P HD video processing (decoding + AI analysis), which is very suitable for various AI applications such as face detection and license plate recognition in video streams.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003ePowerful Network Communication Capabilities: \u003c\/strong\u003eWith dual 1000Mbps Ethernet, the AI box ensures high-speed and stable network communication, meeting the needs of various application scenarios.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eAll-aluminum Alloy Shell: \u003c\/strong\u003eIndustrial-grade all-metal body, aluminum alloy structure, excellent thermal conductivity. The grille design on the top cover effectively conducts heat, ensuring computing performance and stability even under high-temperature operating conditions. The top cover adopts a hexagonal porous design, which is both elegant and efficient.\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eApplications\u003c\/strong\u003e\u003c\/h2\u003e \u003cul\u003e \u003cli\u003eSurveillance\u003c\/li\u003e \u003cli\u003eAI Education\u003c\/li\u003e \u003cli\u003eComputing Services\u003c\/li\u003e \u003cli\u003eEdge Computing\u003c\/li\u003e \u003cli\u003ePrivate Deployment of Large Models\u003c\/li\u003e \u003cli\u003eData Security\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eHardware Overview\u003c\/strong\u003e\u003c\/h2\u003e \u003cp\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-1684X.webp?v=1752722845\"\u003e\u003c\/p\u003e \u003c!----\u003e\u003chr\u003e \u003ch2\u003e \u003c\/h2\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"1\"\u003e \u003ch3\u003eShipping list\u003c\/h3\u003e \u003cul\u003e \u003cli\u003eMain unit × 1\u003c\/li\u003e \u003cli\u003ePower adapter \/ cable (region plug on request) × 1\u003c\/li\u003e \u003cli\u003eAccessories vary by configuration — contact us for the exact included list.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"2\"\u003e \u003cdiv class=\"fx-specs\"\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eShipping list\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eAIBOX-1684X x 1\n12V 4A power adapter x 1\nData cable (Type-C-2.0 data cable) x 1\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSoc\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eSOPHON BM1684X\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eCpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eHigh-performance octa-core ARM A53, 12nm lithography process, frequency up to 2.3 GHz\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eTpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e32TOPS (INT8), 16TFLOPS (FP16\/BF16), 2TFLOPS (FP32)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eVpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e32-channel H.265\/H.264 1080P@25fps video decoding\n1-channel H.265 8K@25fps video decoding\n32-channel 1080P@25fps processing decoding + AI analysis\n12-channel H.265\/H.264 1080P@25fps video encoding\nJPEG image encoding and decoding can reach 1080P@600fps\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eRam\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e8GB\/12GB\/16GB LPDDR4\/LPDDR4X\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eStorage\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e32GB\/64GB\/128GB eMMC, 1 × TF Card\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eDC 12V\/4A (5.5 × 2.5mm)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower consumption\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eNormal: 20.4W (12V\/1700mA)\nMax: 43.2W (12V\/3600mA)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSoftware support\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eThe private deployment of ultra-large-scale parameter models under the Transformer architecture, including large language models such as LLaMa2, ChatGLM, and Qwen, as well as major visual models like ViT, Grounding DINO, and SAM.\nThe private deployment of the Stable Diffusion V1.5 image generation model in the AIGC field.\nTraditional network architectures such as CNN, RNN, and LSTM; a variety of deep learning frameworks, including TensorFlow, PyTorch, MXNet, PaddlePaddle, Caffe, and ONNX, as well as custom operator development.\nDocker container management technology.\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eDimension\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e90.6mm × 84.4mm × 48.5mm\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eWeight\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e≈ 420g\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEnvironment\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eOperating temperature: -20℃~60℃\nStorage temperature: -20℃~70℃\nStorage humidity: 10%~90%RH (non-condensing)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEthernet\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 × Gigabit Ethernet (1000Mbps\/RJ45)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eUsb\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 × USB3.0 (Max: 1A), 1 × Type-C (Debug serial)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eButton\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 × Power button\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eProduct tutorials\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSdk software and firmware files\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"3\"\u003e \u003cdiv class=\"fx-docs\"\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct tutorials\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct datasheet\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eSDK software and firmware files\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eDocument links will be replaced with the official Firefly resource URLs on request.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"4\"\u003e \u003cp\u003e\u003cb\u003eOur cooperating carriers:\u003c\/b\u003e FedEx, DHL, UPS, SF Express\u003c\/p\u003e \u003ch3\u003eDelivery Area And Cost\u003c\/h3\u003e \u003cdiv class=\"fx-scroll\"\u003e \u003ctable class=\"fx-table\"\u003e \u003cthead\u003e\u003ctr\u003e \u003cth\u003eCountry\/Region\u003c\/th\u003e \u003cth\u003e0–2kg\u003c\/th\u003e \u003cth\u003e2–3kg\u003c\/th\u003e \u003cth\u003e3–4kg\u003c\/th\u003e \u003cth\u003e4–5kg\u003c\/th\u003e \u003cth\u003e5–6kg\u003c\/th\u003e \u003cth\u003e6–7kg\u003c\/th\u003e \u003cth\u003e7–8kg\u003c\/th\u003e \u003cth\u003e8–9kg\u003c\/th\u003e \u003cth\u003e9–10kg\u003c\/th\u003e \u003c\/tr\u003e\u003c\/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd\u003eJapan, Taiwan, Hong Kong, Macau\u003c\/td\u003e \u003ctd\u003e$15\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSingapore, Thailand, Malaysia\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eIndonesia, Philippines\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003ctd\u003e$70\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSouth Korea\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eUnited States, Australia, New Zealand, Canada, UK, and most of Western Europe\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$75\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$105\u003c\/td\u003e \u003ctd\u003e$115\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eOther regions (Eastern Europe, Middle East, Latin America, etc.)\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$110\u003c\/td\u003e \u003ctd\u003e$125\u003c\/td\u003e \u003ctd\u003e$135\u003c\/td\u003e \u003ctd\u003e$150\u003c\/td\u003e \u003ctd\u003e$165\u003c\/td\u003e \u003c\/tr\u003e \u003c\/tbody\u003e \u003c\/table\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eShipping time is for reference only; the actual situation shall prevail.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"5\"\u003e\n Why Buy From Ai-Paipai? \u003cul\u003e \u003cli\u003e \u003cb\u003eAuthorized \u0026amp; Genuine\u003c\/b\u003e — sourced directly from brand-approved channels.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eLocal Engineering Support\u003c\/b\u003e — datasheets, SDKs, and pre-flashed images in English and Chinese.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOEM \/ ODM \u0026amp; FPGA Customization\u003c\/b\u003e — tailor specs, enclosures, and BSP for your project.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOne-Stop Sourcing\u003c\/b\u003e — Firefly + youyeetoo + our own FPGA \/ edge lineup in one store.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cstyle\u003e.fx-tabs{margin:24px 0;border:1px solid #e5e7eb;border-radius:10px;overflow:hidden;background:#fff}.fx-tablist{display:flex;flex-wrap:wrap;gap:0;border-bottom:1px solid #e5e7eb;background:#f8fafc}.fx-tab{flex:1 1 auto;min-width:120px;padding:14px 16px;border:0;background:transparent;cursor:pointer;font:600 14px\/1.3 inherit;color:#475569;border-bottom:3px solid transparent;transition:.18s}.fx-tab:hover{color:#0f172a;background:#eef2f7}.fx-tab.is-active{color:#0f172a;border-bottom-color:#2563eb;background:#fff}.fx-panel{display:none;padding:22px 24px}.fx-panel.is-active{display:block}.fx-panel h3{font-size:16px;margin:22px 0 8px;font-weight:700}.fx-panel h3:first-child{margin-top:0}.fx-panel p{margin:10px 0;line-height:1.65}.fx-panel ul{margin:10px 0;padding-left:22px}.fx-panel li{margin:6px 0;line-height:1.6}.fx-auth{background:#f0fdf4;border:1px solid #bbf7d0;border-radius:8px;padding:12px 14px;margin:0 0 16px;font-size:14px;line-height:1.6}.fx-specs{border-top:1px solid #eef2f7}.fx-spec{display:grid;grid-template-columns:230px 1fr;gap:16px;padding:12px 4px;border-bottom:1px solid #eef2f7}.fx-k{font-weight:700;color:#334155}.fx-v{color:#475569}.fx-docs{display:flex;flex-direction:column;gap:10px}.fx-doc{display:flex;justify-content:space-between;align-items:center;gap:12px;padding:12px 14px;border:1px solid #e5e7eb;border-radius:8px}.fx-doc a{color:#2563eb;font-weight:700;text-decoration:none}.fx-doc a:hover{text-decoration:underline}.fx-scroll{overflow-x:auto}.fx-table{border-collapse:collapse;width:100%;min-width:760px;font-size:13px}.fx-table th,.fx-table td{border:1px solid #e5e7eb;padding:8px 10px;text-align:left}.fx-table th{background:#f8fafc;font-weight:700}.fx-note{color:#64748b;font-size:13px;margin-top:12px}\n @media (max-width:749px){.fx-spec{grid-template-columns:1fr;gap:4px}.fx-tab{min-width:50%;flex:1 1 50%}.fx-panel{padding:16px}} \u003c\/style\u003e \u003cscript\u003e\n (function () {\n var roots = document.querySelectorAll('[data-fx-tabs]');\n roots.forEach(function (root) {\n var tabs = root.querySelectorAll('[data-fx-tab]');\n var panels = root.querySelectorAll('[data-fx-panel]');\n tabs.forEach(function (t) {\n t.addEventListener('click', function () {\n var i = t.getAttribute('data-fx-tab');\n tabs.forEach(function (x) { x.classList.toggle('is-active', x === t); });\n panels.forEach(function (p) { p.classList.toggle('is-active', p.getAttribute('data-fx-panel') === i); });\n });\n });\n });\n })(); \u003c\/script\u003e","brand":"Firefly","offers":[{"title":"16G RAM+64G ROM \/ Standard","offer_id":48422534283522,"sku":"firefly-aibox-1684x-ai-box-up-to-32-tops-of-computing-power-41467056685140","price":659.0,"currency_code":"USD","in_stock":true},{"title":"16G RAM+64G ROM \/ Deepseek deployed","offer_id":48422534316290,"sku":"firefly-aibox-1684x-ai-box-up-to-32-tops-of-computing-power-41892657397844","price":689.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0837\/5953\/0242\/files\/AIBox-1688-800800_2.jpg?v=1788244288"},{"product_id":"aibox-orinnx-157tops-ai-big-model-of-edge-computing-jetson-module-nvidia","title":"AIBOX-OrinNX Jetson Orin NX Embedded PC","description":"\u003cp class=\"geo-summary\" style=\"font-size:1rem;line-height:1.65;margin:0 0 1.25rem;padding:0 0 1rem;border-bottom:1px solid #e5e7eb;color:#1f2937\"\u003e\u003cstrong\u003eAIBOX-OrinNX Jetson Orin NX Embedded PC\u003c\/strong\u003e is a Firefly product sold by Ai-Paipai. Key specifications — Cpu: Octa-core 64-bit Arm Cortex-A78AE v8.2 processor, up to… · Ai performance: 157 TOPS · Traditional network architectures: Traditional network architectures such as CNN, RNN, and… · Video output: 1 × HDMI 2.1 (4K@60fps) · Usb: 2× USB 3.0 (Max: 1A). Typical applications: edge AI inference, machine vision and industrial automation. Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.) is an authorized distributor providing local technical support, pre-installed SDK \/ OS images, OEM \/ ODM customization, and worldwide shipping.\u003c\/p\u003e\n\u003c!-- Firefly product tabs --\u003e\n\u003cdiv class=\"fx-tabs\" data-fx-tabs\u003e\n  \u003cdiv class=\"fx-tablist\" role=\"tablist\"\u003e\n    \u003cbutton class=\"fx-tab is-active\" role=\"tab\" data-fx-tab=\"0\"\u003eDescription\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"1\"\u003eWhat's Included\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"2\"\u003eSpecifications\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"3\"\u003eDocuments\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"4\"\u003eShipping Information\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"5\"\u003eWhy Buy From Ai-Paipai?\u003c\/button\u003e\n  \u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel is-active\" data-fx-panel=\"0\"\u003e\n\u003c!-- ===== Firefly product tabs component ===== --\u003e\n\u003cdiv class=\"fx-tabs\" data-fx-tabs\u003e\n  \u003cdiv class=\"fx-tablist\" role=\"tablist\"\u003e\n    \u003cbutton class=\"fx-tab is-active\" role=\"tab\" data-fx-tab=\"0\"\u003eDescription\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"1\"\u003eWhat's Included\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"2\"\u003eSpecifications\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"3\"\u003eDocuments\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"4\"\u003eShipping Information\u003c\/button\u003e\n    \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"5\"\u003e\n  \u003c\/button\u003e\n\u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"1\"\u003e\n    \u003ch3\u003eShipping list\u003c\/h3\u003e\n    \u003cul\u003e\n      \u003cli\u003eMain unit × 1\u003c\/li\u003e\n      \u003cli\u003ePower adapter \/ cable (region plug on request) × 1\u003c\/li\u003e\n      \u003cli\u003eAccessories vary by configuration — contact us for the exact included list.\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"2\"\u003e\n    \u003cdiv class=\"fx-specs\"\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eShipping list\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eAIBOX-OrinNX * 1\nPower Adapter (12V4A, EU\/US\/UK\/AU) * 1\nType-C 2.0 USB Cable * 1\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eAi performance\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e157 TOPS\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eTraditional network architectures\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eTraditional network architectures such as CNN, RNN, and LSTM; a variety of deep learning frameworks include TensorFlow, PyTorch, MXNet, PaddlePaddle, ONNX, and Darknet; custom operator development.\nDocker container management technology facilitates easy image deployment.\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eAi software stack\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eNVIDIA Jetson Orin offers unparalleled AI computing, large unified memory, and comprehensive software stacks, delivering superior energy efficiency to drive the latest generative AI applications. It’s capable of fast inference for any generative AI models powered by the transformer architecture, providing superior edge performance on MLPerf.\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eLarge model\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eRobotic models: ROS models\nLarge language models: The private deployment of ultra-large-scale parameter models under the Transformer architecture, such as LLaMa2, ChatGLM, and Qwen.\nVision models: ViT, Grounding DINO, and SAM.\nAI painting: Stable Diffusion V1.5 image generation model in the AIGC field.\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eCpu\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eOcta-core 64-bit Arm Cortex-A78AE v8.2 processor, up to 2.0GHz\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eGpu\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e1024-core NVIDIA Ampere architecture GPU with 32 Tensor Cores\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003ePower\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eDC 12V (DC 5.5 * 2.1mm)\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003ePower consumption\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eNormal: 7.2W (12V\/600mA)\nMax: 33.6W (12V\/2800mA)\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eVideo output\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e1 × HDMI 2.1 (4K@60fps)\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eOs\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eThe Jetson system, based on Ubuntu 22.04, offers a comprehensive desktop Linux environment with accelerated graphics, supporting libraries such as NVIDIA CUDA, TensorRT, and CuDNN.\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eDimension\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e93.4 mm x 93.4 mm x 50 mm\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eWeight\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e≈ 500g\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eWatchdog\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eSupport external watchdog\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eUsb\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e2× USB 3.0 (Max: 1A)\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eProduct tutorials\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eProduct datasheet\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eSdk software and firmware files\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e\n\u003c\/div\u003e\n    \u003c\/div\u003e\n  \u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"3\"\u003e\n        \u003cdiv class=\"fx-docs\"\u003e\n      \u003cdiv class=\"fx-doc\"\u003e\n\u003cspan\u003eProduct tutorials\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-doc\"\u003e\n\u003cspan\u003eProduct datasheet\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-doc\"\u003e\n\u003cspan\u003eSDK software and firmware files\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e\n\u003c\/div\u003e\n    \u003c\/div\u003e\n    \u003cp class=\"fx-note\"\u003eDocument links will be replaced with the official Firefly resource URLs on request.\u003c\/p\u003e\n  \u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"4\"\u003e\n        \u003cp\u003e\u003cb\u003eOur cooperating carriers:\u003c\/b\u003e FedEx, DHL, UPS, SF Express\u003c\/p\u003e\n    \u003ch3\u003eDelivery Area And Cost\u003c\/h3\u003e\n    \u003cdiv class=\"fx-scroll\"\u003e\n      \u003ctable class=\"fx-table\"\u003e\n        \u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eCountry\/Region\u003c\/th\u003e\n\u003cth\u003e0–2kg\u003c\/th\u003e\n\u003cth\u003e2–3kg\u003c\/th\u003e\n\u003cth\u003e3–4kg\u003c\/th\u003e\n\u003cth\u003e4–5kg\u003c\/th\u003e\n\u003cth\u003e5–6kg\u003c\/th\u003e\n\u003cth\u003e6–7kg\u003c\/th\u003e\n\u003cth\u003e7–8kg\u003c\/th\u003e\n\u003cth\u003e8–9kg\u003c\/th\u003e\n\u003cth\u003e9–10kg\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n        \u003ctbody\u003e\n          \u003ctr\u003e\n\u003ctd\u003eJapan, Taiwan, Hong Kong, Macau\u003c\/td\u003e\n\u003ctd\u003e$15\u003c\/td\u003e\n\u003ctd\u003e$20\u003c\/td\u003e\n\u003ctd\u003e$25\u003c\/td\u003e\n\u003ctd\u003e$30\u003c\/td\u003e\n\u003ctd\u003e$35\u003c\/td\u003e\n\u003ctd\u003e$40\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$50\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eSingapore, Thailand, Malaysia\u003c\/td\u003e\n\u003ctd\u003e$20\u003c\/td\u003e\n\u003ctd\u003e$25\u003c\/td\u003e\n\u003ctd\u003e$30\u003c\/td\u003e\n\u003ctd\u003e$35\u003c\/td\u003e\n\u003ctd\u003e$40\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$50\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003ctd\u003e$60\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eIndonesia, Philippines\u003c\/td\u003e\n\u003ctd\u003e$25\u003c\/td\u003e\n\u003ctd\u003e$30\u003c\/td\u003e\n\u003ctd\u003e$40\u003c\/td\u003e\n\u003ctd\u003e$50\u003c\/td\u003e\n\u003ctd\u003e$60\u003c\/td\u003e\n\u003ctd\u003e$70\u003c\/td\u003e\n\u003ctd\u003e$80\u003c\/td\u003e\n\u003ctd\u003e$85\u003c\/td\u003e\n\u003ctd\u003e$95\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eSouth Korea\u003c\/td\u003e\n\u003ctd\u003e$25\u003c\/td\u003e\n\u003ctd\u003e$35\u003c\/td\u003e\n\u003ctd\u003e$35\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003ctd\u003e$65\u003c\/td\u003e\n\u003ctd\u003e$65\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eUnited States, Australia, New Zealand, Canada, UK, and most of Western Europe\u003c\/td\u003e\n\u003ctd\u003e$30\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003ctd\u003e$65\u003c\/td\u003e\n\u003ctd\u003e$75\u003c\/td\u003e\n\u003ctd\u003e$85\u003c\/td\u003e\n\u003ctd\u003e$95\u003c\/td\u003e\n\u003ctd\u003e$105\u003c\/td\u003e\n\u003ctd\u003e$115\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eOther regions (Eastern Europe, Middle East, Latin America, etc.)\u003c\/td\u003e\n\u003ctd\u003e$50\u003c\/td\u003e\n\u003ctd\u003e$65\u003c\/td\u003e\n\u003ctd\u003e$80\u003c\/td\u003e\n\u003ctd\u003e$95\u003c\/td\u003e\n\u003ctd\u003e$110\u003c\/td\u003e\n\u003ctd\u003e$125\u003c\/td\u003e\n\u003ctd\u003e$135\u003c\/td\u003e\n\u003ctd\u003e$150\u003c\/td\u003e\n\u003ctd\u003e$165\u003c\/td\u003e\n\u003c\/tr\u003e\n        \u003c\/tbody\u003e\n      \u003c\/table\u003e\n    \u003c\/div\u003e\n    \u003cp class=\"fx-note\"\u003eShipping time is for reference only; the actual situation shall prevail.\u003c\/p\u003e\n  \u003c\/div\u003e\n\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"5\"\u003e\n    Why Buy From Ai-Paipai?\n  \u003c\/div\u003e\n\n  \u003c!-- TAB 0: Description --\u003e\n  \u003cdiv class=\"fx-panel is-active\" data-fx-panel=\"0\"\u003e\n    \u003cdiv class=\"fx-auth\"\u003e\n      \u003cb\u003e✅ Authorized Distributor — Ai-Paipai\u003c\/b\u003e\u003cbr\u003e\n      Supplied by an authorized distributor of the original brand. We provide local technical support,\n      pre-installed SDK \/ system images, and OEM \/ ODM customization, plus fast global shipping.\n    \u003c\/div\u003e\n    \u003cp\u003eWith up to 157 TOPS of computing power, AIBOX-OrinNX can run almost all modern AI models, including Transformer and ROS robot models. Implement larger and more complex deep neural networks, such as using TensorFlow, OpenCV, JetPack, MXNet, PyTorch, etc., to achieve object recognition, target detection and tracking, speech recognition, and other visual development functions, and adapt to a variety of AI application scenarios.\u003c\/p\u003e\n\n    \u003ch3\u003eApplication Cases\u003c\/h3\u003e\n    \u003cul\u003e\n      \u003cli\u003eBackground Removal via U²-Net\u003c\/li\u003e\n      \u003cli\u003eMonocular Depth Estimation\u003c\/li\u003e\n    \u003c\/ul\u003e\n\n    \u003ch3\u003eFeature\u003c\/h3\u003e\n    \u003cul\u003e\n      \u003cli\u003e\n\u003cb\u003eHigh-performance Edge Computing Jetson Orin NX Module:\u003c\/b\u003e The NVIDIA Jetson Orin NX edge computing module (16GB version) is equipped with an eight-core ARM CPU and a 1024-core NVIDIA Ampere architecture GPU (including 32 Tensor Cores), which can run multiple AI application pipelines simultaneously and provide powerful inference performance.\u003c\/li\u003e\n      \u003cli\u003e\n\u003cb\u003eUp to 157 TOPS of Computing Power:\u003c\/b\u003e The AIBOX-OrinNX provides up to 157 TOPS of computing power and is equipped with a 128GB PCIe NVMe SSD. The Ubuntu 22.04-based JETSON system provides a comprehensive desktop Linux environment with accelerated graphics capabilities and support for libraries such as NVIDIA CUDA, TensorRT, and CuDNN.\u003c\/li\u003e\n      \u003cli\u003e\n\u003cb\u003eSupport 18-channel 1080p@30fps H.265 Video Decoding:\u003c\/b\u003e Supports up to 1×8K30 (H.265), 2×4K60 (H.265), 4×4K30 (H.265), 9×1080p60 (H.265), and 18×1080p30 (H.265) video decoding to meet the needs of diverse AI application scenarios.\u003c\/li\u003e\n      \u003cli\u003e\n\u003cb\u003eAluminum Alloy Enclosure With Efficient Heat Dissipation:\u003c\/b\u003e Industrial-grade full metal shell and aluminum alloy structure with excellent thermal conductivity. The grille design on the top cover effectively conducts heat and ensures computing performance and stability even under high-temperature operating conditions.\u003c\/li\u003e\n    \u003c\/ul\u003e\n\n    \u003ch3\u003eApplications\u003c\/h3\u003e\n    \u003cul\u003e\n      \u003cli\u003e\n\u003cb\u003eAI Software Stack and Ecosystem:\u003c\/b\u003e Enable edge AI and robotics development with the world's most comprehensive AI software stack and ecosystem, powered by generative AI at the edge and the NVIDIA Metropolis and Isaac platforms. NVIDIA JetPack, Isaac ROS, and reference AI workflows seamlessly integrate cutting-edge technologies into your products.\u003c\/li\u003e\n      \u003cli\u003e\n\u003cb\u003eGenerative AI at The Edge:\u003c\/b\u003e NVIDIA Jetson Orin provides unparalleled AI computing power, large unified memory, and a comprehensive software stack with excellent energy efficiency to drive the latest generative AI applications.\u003c\/li\u003e\n      \u003cli\u003e\n\u003cb\u003eThe Private Deployment of Large Models:\u003c\/b\u003e Large language models; Vision models; AI painting; Traditional network architectures; Deep learning frameworks; Docker containerization.\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n\n  \u003c!-- TAB 1: What's Included --\u003e\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"1\"\u003e\n    \u003ch3\u003eShipping list\u003c\/h3\u003e\n    \u003cul\u003e\n      \u003cli\u003eAIBOX-OrinNX * 1\u003c\/li\u003e\n      \u003cli\u003ePower Adapter (12V4A, EU\/US\/UK\/AU) * 1\u003c\/li\u003e\n      \u003cli\u003eType-C 2.0 USB Cable * 1\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n\n  \u003c!-- TAB 2: Specifications --\u003e\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"2\"\u003e\n    \u003cdiv class=\"fx-specs\"\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eAi performance\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e157 TOPS\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eTraditional network architectures\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eTraditional network architectures such as CNN, RNN, and LSTM; a variety of deep learning frameworks include TensorFlow, PyTorch, MXNet, PaddlePaddle, ONNX, and Darknet; custom operator development.\u003cbr\u003eDocker container management technology facilitates easy image deployment.\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eAi software stack\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eNVIDIA Jetson Orin offers unparalleled AI computing, large unified memory, and comprehensive software stacks, delivering superior energy efficiency to drive the latest generative AI applications. It's capable of fast inference for any generative AI models powered by the transformer architecture, providing superior edge performance on MLPerf.\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eLarge model\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eRobotic models: ROS models\u003cbr\u003eLarge language models: The private deployment of ultra-large-scale parameter models under the Transformer architecture, such as LLaMa2, ChatGLM, and Qwen.\u003cbr\u003eVision models: ViT, Grounding DINO, and SAM.\u003cbr\u003eAI painting: Stable Diffusion V1.5 image generation model in the AIGC field.\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eCPU\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eOcta-core 64-bit Arm Cortex-A78AE v8.2 processor, up to 2.0GHz\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eGPU\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e1024-core NVIDIA Ampere architecture GPU with 32 Tensor Cores\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003ePower\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eDC 12V (DC 5.5 * 2.1mm)\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003ePower consumption\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eNormal: 7.2W (12V\/600mA)\u003cbr\u003eMax: 33.6W (12V\/2800mA)\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eVideo output\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e1 × HDMI 2.1 (4K@60fps)\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eOS\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eThe Jetson system, based on Ubuntu 22.04, offers a comprehensive desktop Linux environment with accelerated graphics, supporting libraries such as NVIDIA CUDA, TensorRT, and CuDNN.\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eDimension\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e93.4 mm x 93.4 mm x 50 mm\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eWeight\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e≈ 500g\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eWatchdog\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003eSupport external watchdog\u003c\/div\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-spec\"\u003e\n\u003cdiv class=\"fx-k\"\u003eUSB\u003c\/div\u003e\n\u003cdiv class=\"fx-v\"\u003e2× USB 3.0 (Max: 1A)\u003c\/div\u003e\n\u003c\/div\u003e\n    \u003c\/div\u003e\n  \u003c\/div\u003e\n\n  \u003c!-- TAB 3: Documents --\u003e\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"3\"\u003e\n    \u003cdiv class=\"fx-docs\"\u003e\n      \u003cdiv class=\"fx-doc\"\u003e\n\u003cspan\u003eProduct tutorials\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-doc\"\u003e\n\u003cspan\u003eProduct datasheet\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e\n\u003c\/div\u003e\n      \u003cdiv class=\"fx-doc\"\u003e\n\u003cspan\u003eSdk software and firmware files\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e\n\u003c\/div\u003e\n    \u003c\/div\u003e\n    \u003cp class=\"fx-note\"\u003eDocument links will be replaced with the official Firefly resource URLs.\u003c\/p\u003e\n  \u003c\/div\u003e\n\n  \u003c!-- TAB 4: Shipping Information --\u003e\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"4\"\u003e\n    \u003cp\u003e\u003cb\u003eOur cooperating carriers:\u003c\/b\u003e FedEx, DHL, UPS, SF Express\u003c\/p\u003e\n    \u003ch3\u003eDelivery Area And Cost\u003c\/h3\u003e\n    \u003cdiv class=\"fx-scroll\"\u003e\n      \u003ctable class=\"fx-table\"\u003e\n        \u003cthead\u003e\u003ctr\u003e\n          \u003cth\u003eCountry\/Region\u003c\/th\u003e\n\u003cth\u003e0–2kg\u003c\/th\u003e\n\u003cth\u003e2–3kg\u003c\/th\u003e\n\u003cth\u003e3–4kg\u003c\/th\u003e\n\u003cth\u003e4–5kg\u003c\/th\u003e\n          \u003cth\u003e5–6kg\u003c\/th\u003e\n\u003cth\u003e6–7kg\u003c\/th\u003e\n\u003cth\u003e7–8kg\u003c\/th\u003e\n\u003cth\u003e8–9kg\u003c\/th\u003e\n\u003cth\u003e9–10kg\u003c\/th\u003e\n        \u003c\/tr\u003e\u003c\/thead\u003e\n        \u003ctbody\u003e\n          \u003ctr\u003e\n\u003ctd\u003eJapan, Taiwan, Hong Kong, Macau\u003c\/td\u003e\n\u003ctd\u003e$15\u003c\/td\u003e\n\u003ctd\u003e$20\u003c\/td\u003e\n\u003ctd\u003e$25\u003c\/td\u003e\n\u003ctd\u003e$30\u003c\/td\u003e\n\u003ctd\u003e$35\u003c\/td\u003e\n\u003ctd\u003e$40\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$50\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eSingapore, Thailand, Malaysia\u003c\/td\u003e\n\u003ctd\u003e$20\u003c\/td\u003e\n\u003ctd\u003e$25\u003c\/td\u003e\n\u003ctd\u003e$30\u003c\/td\u003e\n\u003ctd\u003e$35\u003c\/td\u003e\n\u003ctd\u003e$40\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$50\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003ctd\u003e$60\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eIndonesia, Philippines\u003c\/td\u003e\n\u003ctd\u003e$25\u003c\/td\u003e\n\u003ctd\u003e$30\u003c\/td\u003e\n\u003ctd\u003e$40\u003c\/td\u003e\n\u003ctd\u003e$50\u003c\/td\u003e\n\u003ctd\u003e$60\u003c\/td\u003e\n\u003ctd\u003e$70\u003c\/td\u003e\n\u003ctd\u003e$80\u003c\/td\u003e\n\u003ctd\u003e$85\u003c\/td\u003e\n\u003ctd\u003e$95\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eSouth Korea\u003c\/td\u003e\n\u003ctd\u003e$25\u003c\/td\u003e\n\u003ctd\u003e$35\u003c\/td\u003e\n\u003ctd\u003e$35\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003ctd\u003e$65\u003c\/td\u003e\n\u003ctd\u003e$65\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eUnited States, Australia, New Zealand, Canada, UK, and most of Western Europe\u003c\/td\u003e\n\u003ctd\u003e$30\u003c\/td\u003e\n\u003ctd\u003e$45\u003c\/td\u003e\n\u003ctd\u003e$55\u003c\/td\u003e\n\u003ctd\u003e$65\u003c\/td\u003e\n\u003ctd\u003e$75\u003c\/td\u003e\n\u003ctd\u003e$85\u003c\/td\u003e\n\u003ctd\u003e$95\u003c\/td\u003e\n\u003ctd\u003e$105\u003c\/td\u003e\n\u003ctd\u003e$115\u003c\/td\u003e\n\u003c\/tr\u003e\n          \u003ctr\u003e\n\u003ctd\u003eOther regions (Eastern Europe, Middle East, Latin America, etc.)\u003c\/td\u003e\n\u003ctd\u003e$50\u003c\/td\u003e\n\u003ctd\u003e$65\u003c\/td\u003e\n\u003ctd\u003e$80\u003c\/td\u003e\n\u003ctd\u003e$95\u003c\/td\u003e\n\u003ctd\u003e$110\u003c\/td\u003e\n\u003ctd\u003e$125\u003c\/td\u003e\n\u003ctd\u003e$135\u003c\/td\u003e\n\u003ctd\u003e$150\u003c\/td\u003e\n\u003ctd\u003e$165\u003c\/td\u003e\n\u003c\/tr\u003e\n        \u003c\/tbody\u003e\n      \u003c\/table\u003e\n    \u003c\/div\u003e\n    \u003cp class=\"fx-note\"\u003eShipping time is for reference only; the actual situation shall prevail.\u003c\/p\u003e\n  \u003c\/div\u003e\n\n  \u003c!-- TAB 5: Why Buy From Ai-Paipai --\u003e\n  \u003cdiv class=\"fx-panel\" data-fx-panel=\"5\"\u003e\n    \u003cul\u003e\n      \u003cli\u003e\n\u003cb\u003eAuthorized distributor\u003c\/b\u003e — genuine products with full manufacturer warranty.\u003c\/li\u003e\n      \u003cli\u003e\n\u003cb\u003eLocal technical support\u003c\/b\u003e — pre-installed SDK \/ system images, ready to run out of the box.\u003c\/li\u003e\n      \u003cli\u003e\n\u003cb\u003eOEM \/ ODM customization\u003c\/b\u003e — carrier board, enclosure, I\/O and branding options.\u003c\/li\u003e\n      \u003cli\u003e\n\u003cb\u003eFast global shipping\u003c\/b\u003e — FedEx \/ DHL \/ UPS \/ SF Express, tracked door to door.\u003c\/li\u003e\n      \u003cli\u003e\n\u003cb\u003eVolume pricing\u003c\/b\u003e — contact us for project and distributor pricing.\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e\n\n\u003cstyle\u003e\n  .fx-tabs{margin:24px 0;border:1px solid #e5e7eb;border-radius:10px;overflow:hidden;background:#fff}\n  .fx-tablist{display:flex;flex-wrap:wrap;gap:0;border-bottom:1px solid #e5e7eb;background:#f8fafc}\n  .fx-tab{flex:1 1 auto;min-width:120px;padding:14px 16px;border:0;background:transparent;cursor:pointer;\n    font:600 14px\/1.3 inherit;color:#475569;border-bottom:3px solid transparent;transition:.18s}\n  .fx-tab:hover{color:#0f172a;background:#eef2f7}\n  .fx-tab.is-active{color:#0f172a;border-bottom-color:#2563eb;background:#fff}\n  .fx-panel{display:none;padding:22px 24px}\n  .fx-panel.is-active{display:block}\n  .fx-panel h3{font-size:16px;margin:22px 0 8px;font-weight:700}\n  .fx-panel h3:first-child{margin-top:0}\n  .fx-panel p{margin:10px 0;line-height:1.65}\n  .fx-panel ul{margin:10px 0;padding-left:22px}\n  .fx-panel li{margin:6px 0;line-height:1.6}\n  .fx-auth{background:#f0fdf4;border:1px solid #bbf7d0;border-radius:8px;padding:12px 14px;margin:0 0 16px;font-size:14px;line-height:1.6}\n  .fx-specs{border-top:1px solid #eef2f7}\n  .fx-spec{display:grid;grid-template-columns:230px 1fr;gap:16px;padding:12px 4px;border-bottom:1px solid #eef2f7}\n  .fx-k{font-weight:700;color:#334155}\n  .fx-v{color:#475569}\n  .fx-docs{display:flex;flex-direction:column;gap:10px}\n  .fx-doc{display:flex;justify-content:space-between;align-items:center;gap:12px;padding:12px 14px;border:1px solid #e5e7eb;border-radius:8px}\n  .fx-doc a{color:#2563eb;font-weight:700;text-decoration:none}\n  .fx-doc a:hover{text-decoration:underline}\n  .fx-scroll{overflow-x:auto}\n  .fx-table{border-collapse:collapse;width:100%;min-width:760px;font-size:13px}\n  .fx-table th,.fx-table td{border:1px solid #e5e7eb;padding:8px 10px;text-align:left}\n  .fx-table th{background:#f8fafc;font-weight:700}\n  .fx-note{color:#64748b;font-size:13px;margin-top:12px}\n  @media (max-width:749px){\n    .fx-spec{grid-template-columns:1fr;gap:4px}\n    .fx-tab{min-width:50%;flex:1 1 50%}\n    .fx-panel{padding:16px}\n  }\n\u003c\/style\u003e\n\n\u003cscript\u003e\n  (function () {\n    var roots = document.querySelectorAll('[data-fx-tabs]');\n    roots.forEach(function (root) {\n      var tabs = root.querySelectorAll('[data-fx-tab]');\n      var panels = root.querySelectorAll('[data-fx-panel]');\n      tabs.forEach(function (t) {\n        t.addEventListener('click', function () {\n          var i = t.getAttribute('data-fx-tab');\n          tabs.forEach(function (x) { x.classList.toggle('is-active', x === t); });\n          panels.forEach(function (p) { p.classList.toggle('is-active', p.getAttribute('data-fx-panel') === i); });\n        });\n      });\n    });\n  })();\n\u003c\/script\u003e\n\n  \u003c\/div\u003e\n\u003c\/div\u003e\n\n\u003cstyle\u003e\n  .fx-tabs{margin:24px 0;border:1px solid #e5e7eb;border-radius:10px;overflow:hidden;background:#fff}\n  .fx-tablist{display:flex;flex-wrap:wrap;gap:0;border-bottom:1px solid #e5e7eb;background:#f8fafc}\n  .fx-tab{flex:1 1 auto;min-width:120px;padding:14px 16px;border:0;background:transparent;cursor:pointer;font:600 14px\/1.3 inherit;color:#475569;border-bottom:3px solid transparent;transition:.18s}\n  .fx-tab:hover{color:#0f172a;background:#eef2f7}\n  .fx-tab.is-active{color:#0f172a;border-bottom-color:#2563eb;background:#fff}\n  .fx-panel{display:none;padding:22px 24px}\n  .fx-panel.is-active{display:block}\n  .fx-panel h3{font-size:16px;margin:22px 0 8px;font-weight:700}\n  .fx-panel h3:first-child{margin-top:0}\n  .fx-panel p{margin:10px 0;line-height:1.65}\n  .fx-panel ul{margin:10px 0;padding-left:22px}\n  .fx-panel li{margin:6px 0;line-height:1.6}\n  .fx-auth{background:#f0fdf4;border:1px solid #bbf7d0;border-radius:8px;padding:12px 14px;margin:0 0 16px;font-size:14px;line-height:1.6}\n  .fx-specs{border-top:1px solid #eef2f7}\n  .fx-spec{display:grid;grid-template-columns:230px 1fr;gap:16px;padding:12px 4px;border-bottom:1px solid #eef2f7}\n  .fx-k{font-weight:700;color:#334155}\n  .fx-v{color:#475569}\n  .fx-docs{display:flex;flex-direction:column;gap:10px}\n  .fx-doc{display:flex;justify-content:space-between;align-items:center;gap:12px;padding:12px 14px;border:1px solid #e5e7eb;border-radius:8px}\n  .fx-doc a{color:#2563eb;font-weight:700;text-decoration:none}\n  .fx-doc a:hover{text-decoration:underline}\n  .fx-scroll{overflow-x:auto}\n  .fx-table{border-collapse:collapse;width:100%;min-width:760px;font-size:13px}\n  .fx-table th,.fx-table td{border:1px solid #e5e7eb;padding:8px 10px;text-align:left}\n  .fx-table th{background:#f8fafc;font-weight:700}\n  .fx-note{color:#64748b;font-size:13px;margin-top:12px}\n  @media (max-width:749px){.fx-spec{grid-template-columns:1fr;gap:4px}.fx-tab{min-width:50%;flex:1 1 50%}.fx-panel{padding:16px}}\n\u003c\/style\u003e\n\n\u003cscript\u003e\n  (function () {\n    var roots = document.querySelectorAll('[data-fx-tabs]');\n    roots.forEach(function (root) {\n      var tabs = root.querySelectorAll('[data-fx-tab]');\n      var panels = root.querySelectorAll('[data-fx-panel]');\n      tabs.forEach(function (t) {\n        t.addEventListener('click', function () {\n          var i = t.getAttribute('data-fx-tab');\n          tabs.forEach(function (x) { x.classList.toggle('is-active', x === t); });\n          panels.forEach(function (p) { p.classList.toggle('is-active', p.getAttribute('data-fx-panel') === i); });\n        });\n      });\n    });\n  })();\n\u003c\/script\u003e","brand":"Firefly","offers":[{"title":"16G RAM+128G SSD \/ Standard without Wifi","offer_id":48422538739970,"sku":"firefly-aibox-orinnx-157tops-ai-big-model-of-edge-computing-jetson-module-nvidia-42231437131860","price":1539.0,"currency_code":"USD","in_stock":true},{"title":"16G RAM+128G SSD \/ Deepseek Deployed without Wifi","offer_id":48422538772738,"sku":"firefly-aibox-orinnx-157tops-ai-big-model-of-edge-computing-jetson-module-nvidia-42231474061396","price":1559.0,"currency_code":"USD","in_stock":true},{"title":"16G RAM+256G SSD \/ Standard without Wifi","offer_id":48422538805506,"sku":"firefly-aibox-orinnx-157tops-ai-big-model-of-edge-computing-jetson-module-nvidia-45300359069780","price":1649.0,"currency_code":"USD","in_stock":true},{"title":"16G RAM+256G SSD \/ Deepseek Deployed without Wifi","offer_id":48422538838274,"sku":"firefly-aibox-orinnx-157tops-ai-big-model-of-edge-computing-jetson-module-nvidia-45300359102548","price":1669.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0837\/5953\/0242\/files\/800800-1.jpg?v=1788244361"},{"product_id":"aibox-3588-artificial-intelligence-box-6t-large-model-privatization-deployment-edge-computing-ruixin-micro-rk3588","title":"AIBOX-3588 RK3588 Edge Computing Fanless Industrial PC","description":"\u003cp class=\"geo-summary\" style=\"font-size:1rem;line-height:1.65;margin:0 0 1.25rem;padding:0 0 1rem;border-bottom:1px solid #e5e7eb;color:#1f2937\"\u003e\u003cstrong\u003eAIBOX-3588 RK3588 Edge Computing Fanless Industrial PC\u003c\/strong\u003e is a Firefly product sold by Ai-Paipai. Key specifications — Soc: Rockchip RK3588 · Npu: 6 TOPS NPU, supports INT4\/INT8\/INT16 mixed operations · Ram: LPDDR4 (4GB\/8GB\/16GB\/32GB optional) · Storage: eMMC (16GB\/32GB\/64GB\/128GB\/256GB optional) · Ethernet: 2 × Gigabit Ethernet (1000Mbps\/RJ45). Typical applications: edge AI inference, industrial automation and digital signage and HMI. Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.) is an authorized distributor providing local technical support, pre-installed SDK \/ OS images, OEM \/ ODM customization, and worldwide shipping.\u003c\/p\u003e \u003c!-- Firefly product tabs --\u003e \u003cdiv class=\"fx-tabs\" data-fx-tabs\u003e \u003cdiv class=\"fx-tablist\" role=\"tablist\"\u003e \u003cbutton class=\"fx-tab is-active\" role=\"tab\" data-fx-tab=\"0\"\u003eDescription\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"1\"\u003eWhat's Included\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"2\"\u003eSpecifications\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"3\"\u003eDocuments\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"4\"\u003eShipping Information\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"5\"\u003eWhy Buy From Ai-Paipai?\u003c\/button\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel is-active\" data-fx-panel=\"0\"\u003e \u003cdiv style=\"border:2px solid #2b6cb0;background:#f0f7ff;padding:14px 18px;margin:0 0 18px;border-radius:8px;\"\u003e \u003ch3 style=\"margin:0 0 6px;color:#2b6cb0;\"\u003e✅ Authorized Distributor — Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.)\u003c\/h3\u003e \u003cp style=\"margin:0;font-size:14px;\"\u003eThis product is supplied by an \u003cb\u003eauthorized distributor\u003c\/b\u003e of the original brand.\nWe provide \u003cb\u003elocal technical support, pre-installed SDK \/ mirror images, and OEM \/ ODM customization\u003c\/b\u003e, plus fast global shipping.\u003c\/p\u003e \u003c\/div\u003e \u003cp\u003eAIBOX-3588 low-power large-model embedded PC supports mainstream large-model private deployment, privatizing AI computing power, and one box can meet personalized AI deployment! The host features a built-in ARM Mali G52 MC3 GPU, offering computing power of up to 6 TOPS. This enables more intelligent data processing, voice recognition, and image analysis, meeting the edge computing AI application needs of most terminal devices.\u003c\/p\u003e \u003cul\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-3576_AIBOX-3588_AIBOX-3588S_Specification_EN_322a58d6-5294-475c-b4d9-7e256dcc2f13.pdf?v=1751264101\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Wiki: \u003ca href=\"https:\/\/wiki.t-firefly.com\/en\/AIBOX-3588\/index.html\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 18px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e \u003cul\u003e \u003cli\u003e \u003cstrong\u003eThe Private Deployment of Large Models: \u003c\/strong\u003eThis embedded PC provides up to 6 TOPS of computing power, enabling advanced intelligent data processing, voice recognition, image analysis, and other functions, effectively meeting the AI application needs of various terminal devices for edge computing.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eOcta-core 64-bit AIOT Processor RK3588: \u003c\/strong\u003e RK3588, a new generation of octa-core 64-bit high-performance AIoT processor RK3588, adopts 8nm LP process and has a maximum main frequency of 2.4GHz.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003e8K@60fps  H.265\/VP9 Video Decoding: \u003c\/strong\u003eSupports 8K@60fps H.265\/VP9 video decoding and 8K@30fps H.265\/H.264 video encoding, and can encode and decode simultaneously.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eStrong Network Communication Capability: \u003c\/strong\u003eEquipped with dual 1000Mbps Ethernet to ensure high-speed and stable network communication.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eAlloy Shell, Efficient Heat Dissipation: \u003c\/strong\u003eEquipped with a full metal shell and aluminum alloy structure for heat conduction, the side of the top cover shell adopts a banner grille design to ensure external air circulation and efficient heat dissipation, ensuring computing performance and stability during high-temperature operation.\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 18px;\"\u003e\u003cstrong\u003eApplications\u003c\/strong\u003e\u003c\/h2\u003e \u003cul\u003e \u003cli\u003eIntelligent Surveillance\u003c\/li\u003e \u003cli\u003eAI Intelligent Teaching\u003c\/li\u003e \u003cli\u003eEdge Computing\u003c\/li\u003e \u003cli\u003eLarge Language Model\u003c\/li\u003e \u003cli\u003eData Security\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eHardware Overview\u003c\/strong\u003e\u003c\/h2\u003e \u003cp\u003e\u003cstrong\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-3576.webp?v=1750749691\"\u003e\u003c\/strong\u003e\u003c\/p\u003e \u003chr\u003e \u003ch2\u003e \u003c\/h2\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"1\"\u003e \u003ch3\u003eShipping list\u003c\/h3\u003e \u003cul\u003e \u003cli\u003eMain unit × 1\u003c\/li\u003e \u003cli\u003ePower adapter \/ cable (region plug on request) × 1\u003c\/li\u003e \u003cli\u003eAccessories vary by configuration — contact us for the exact included list.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"2\"\u003e \u003cdiv class=\"fx-specs\"\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eShipping list\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eAIBOX-3588*1\n12V4A Power Adapter*1\nUSB Type-C Cable\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSoc\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eRockchip RK3588\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eCpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eOcta-core 64-bit processor (4×Cortex-A76+4×Cortex-A55), main frequency up to 2.4 GHz\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eGpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eARM Mali-G610 MP4 quad-core GPU, supports OpenGL ES3.2\/OpenCL 2.2\/Vulkan1.1, 450 GFLOPS\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eNpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e6 TOPS NPU, supports INT4\/INT8\/INT16 mixed operations\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eVpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eDecode: 8K@60fps\/4K@120fpsH.265\/VP9\/AVS2, 8K@30fps H.264 AVC\/MVC, 4K@60fps AV1, 1080P@60fps MPEG-2\/-1\/VC-1\/VP8\nEncode: 8K@30fps H.265\/H.264\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eRam\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eLPDDR4 (4GB\/8GB\/16GB\/32GB optional)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eStorage\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eeMMC (16GB\/32GB\/64GB\/128GB\/256GB optional)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eStorage expansion\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 × M.2 (Expandable SATA 3.0\/PCIe NVMe SSD, supports 2242\/2260\/2280; Inside the computer, M.2 multiplexed with lower USB3.0), 1 × TF Card\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eDC 12V\/2A (5.5 × 2.1mm)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower consumption\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eNormal: 2.64W(12V\/220mA)\nMax:14.4W(12V\/1200mA)\nMin(Sleep):0.18W(12V\/15mA)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eVideo output\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 × HDMI2.1(8K@60fps)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eOs\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eLinux OS (Ubuntu)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSoftware support\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e・Support the privatization deployment of ultra-large-scale parametric models under the Transformer architecture, such as Gemma series, ChatGLM series, Qwen series, Phi series and other large language models\n・It supports traditional network architectures such as CNN, RNN, and LSTM, and supports the import and export of RKNN models; Support a variety of deep learning frameworks, including TensorFlow, TensorFlow Lite, PyTorch, Caffe, ONNX and Darknet. It also supports the development of custom operators\n・Support Docker container management technology\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eDimension\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e93.4mm × 93.4mm × 50mm\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eWeight\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e≈ 500g\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEnvironment\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eOperating: -20℃~60℃\nStorage: -20℃~70℃\nStorage Humidity: 10%~90%RH (non-condensing)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEthernet\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 × Gigabit Ethernet (1000Mbps\/RJ45)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eUsb\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 × USB3.0(Max:1A),\n1 × Type-C(Can be used as a firmware flashing port. Set to USB2.0 HOST after booting up)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eButton\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 × Power, 1 × MaskRom\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eProduct tutorials\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eProduct datasheet\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSdk software and firmware files\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"3\"\u003e \u003cdiv class=\"fx-docs\"\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct tutorials\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct datasheet\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eSDK software and firmware files\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eDocument links will be replaced with the official Firefly resource URLs on request.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"4\"\u003e \u003cp\u003e\u003cb\u003eOur cooperating carriers:\u003c\/b\u003e FedEx, DHL, UPS, SF Express\u003c\/p\u003e \u003ch3\u003eDelivery Area And Cost\u003c\/h3\u003e \u003cdiv class=\"fx-scroll\"\u003e \u003ctable class=\"fx-table\"\u003e \u003cthead\u003e\u003ctr\u003e \u003cth\u003eCountry\/Region\u003c\/th\u003e \u003cth\u003e0–2kg\u003c\/th\u003e \u003cth\u003e2–3kg\u003c\/th\u003e \u003cth\u003e3–4kg\u003c\/th\u003e \u003cth\u003e4–5kg\u003c\/th\u003e \u003cth\u003e5–6kg\u003c\/th\u003e \u003cth\u003e6–7kg\u003c\/th\u003e \u003cth\u003e7–8kg\u003c\/th\u003e \u003cth\u003e8–9kg\u003c\/th\u003e \u003cth\u003e9–10kg\u003c\/th\u003e \u003c\/tr\u003e\u003c\/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd\u003eJapan, Taiwan, Hong Kong, Macau\u003c\/td\u003e \u003ctd\u003e$15\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSingapore, Thailand, Malaysia\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eIndonesia, Philippines\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003ctd\u003e$70\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSouth Korea\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eUnited States, Australia, New Zealand, Canada, UK, and most of Western Europe\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$75\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$105\u003c\/td\u003e \u003ctd\u003e$115\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eOther regions (Eastern Europe, Middle East, Latin America, etc.)\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$110\u003c\/td\u003e \u003ctd\u003e$125\u003c\/td\u003e \u003ctd\u003e$135\u003c\/td\u003e \u003ctd\u003e$150\u003c\/td\u003e \u003ctd\u003e$165\u003c\/td\u003e \u003c\/tr\u003e \u003c\/tbody\u003e \u003c\/table\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eShipping time is for reference only; the actual situation shall prevail.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"5\"\u003e\n Why Buy From Ai-Paipai? \u003cul\u003e \u003cli\u003e \u003cb\u003eAuthorized \u0026amp; Genuine\u003c\/b\u003e — sourced directly from brand-approved channels.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eLocal Engineering Support\u003c\/b\u003e — datasheets, SDKs, and pre-flashed images in English and Chinese.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOEM \/ ODM \u0026amp; FPGA Customization\u003c\/b\u003e — tailor specs, enclosures, and BSP for your project.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOne-Stop Sourcing\u003c\/b\u003e — Firefly + youyeetoo + our own FPGA \/ edge lineup in one store.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cstyle\u003e.fx-tabs{margin:24px 0;border:1px solid #e5e7eb;border-radius:10px;overflow:hidden;background:#fff}.fx-tablist{display:flex;flex-wrap:wrap;gap:0;border-bottom:1px solid #e5e7eb;background:#f8fafc}.fx-tab{flex:1 1 auto;min-width:120px;padding:14px 16px;border:0;background:transparent;cursor:pointer;font:600 14px\/1.3 inherit;color:#475569;border-bottom:3px solid transparent;transition:.18s}.fx-tab:hover{color:#0f172a;background:#eef2f7}.fx-tab.is-active{color:#0f172a;border-bottom-color:#2563eb;background:#fff}.fx-panel{display:none;padding:22px 24px}.fx-panel.is-active{display:block}.fx-panel h3{font-size:16px;margin:22px 0 8px;font-weight:700}.fx-panel h3:first-child{margin-top:0}.fx-panel p{margin:10px 0;line-height:1.65}.fx-panel ul{margin:10px 0;padding-left:22px}.fx-panel li{margin:6px 0;line-height:1.6}.fx-auth{background:#f0fdf4;border:1px solid #bbf7d0;border-radius:8px;padding:12px 14px;margin:0 0 16px;font-size:14px;line-height:1.6}.fx-specs{border-top:1px solid #eef2f7}.fx-spec{display:grid;grid-template-columns:230px 1fr;gap:16px;padding:12px 4px;border-bottom:1px solid #eef2f7}.fx-k{font-weight:700;color:#334155}.fx-v{color:#475569}.fx-docs{display:flex;flex-direction:column;gap:10px}.fx-doc{display:flex;justify-content:space-between;align-items:center;gap:12px;padding:12px 14px;border:1px solid #e5e7eb;border-radius:8px}.fx-doc a{color:#2563eb;font-weight:700;text-decoration:none}.fx-doc a:hover{text-decoration:underline}.fx-scroll{overflow-x:auto}.fx-table{border-collapse:collapse;width:100%;min-width:760px;font-size:13px}.fx-table th,.fx-table td{border:1px solid #e5e7eb;padding:8px 10px;text-align:left}.fx-table th{background:#f8fafc;font-weight:700}.fx-note{color:#64748b;font-size:13px;margin-top:12px}\n @media (max-width:749px){.fx-spec{grid-template-columns:1fr;gap:4px}.fx-tab{min-width:50%;flex:1 1 50%}.fx-panel{padding:16px}} \u003c\/style\u003e \u003cscript\u003e\n (function () {\n var roots = document.querySelectorAll('[data-fx-tabs]');\n roots.forEach(function (root) {\n var tabs = root.querySelectorAll('[data-fx-tab]');\n var panels = root.querySelectorAll('[data-fx-panel]');\n tabs.forEach(function (t) {\n t.addEventListener('click', function () {\n var i = t.getAttribute('data-fx-tab');\n tabs.forEach(function (x) { x.classList.toggle('is-active', x === t); });\n panels.forEach(function (p) { p.classList.toggle('is-active', p.getAttribute('data-fx-panel') === i); });\n });\n });\n });\n })(); \u003c\/script\u003e","brand":"Firefly","offers":[{"title":"8G RAM+64G ROM \/ Standard","offer_id":48422539919618,"sku":"firefly-aibox-3588-artificial-intelligence-box-6t-large-model-privatization-deployment-edge-computing-ruixin-micro-rk3588-41712186359892","price":449.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+64G ROM \/ Deepseek deployed","offer_id":48422539952386,"sku":"firefly-aibox-3588-artificial-intelligence-box-6t-large-model-privatization-deployment-edge-computing-ruixin-micro-rk3588-41892662673492","price":469.0,"currency_code":"USD","in_stock":true},{"title":"16G RAM+256G ROM \/ Standard","offer_id":48422539985154,"sku":"firefly-aibox-3588-artificial-intelligence-box-6t-large-model-privatization-deployment-edge-computing-ruixin-micro-rk3588-41967860678740","price":679.0,"currency_code":"USD","in_stock":true},{"title":"16G RAM+256G ROM \/ Deepseek deployed","offer_id":48422540017922,"sku":"firefly-aibox-3588-artificial-intelligence-box-6t-large-model-privatization-deployment-edge-computing-ruixin-micro-rk3588-41967860711508","price":699.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0837\/5953\/0242\/files\/AIBox-3588-800800_2.jpg?v=1788244366"},{"product_id":"aibox-3576-large-model-ai-box","title":"AIBOX-3576 RK3576 Fanless ARM Linux Mini PC","description":"\u003cp class=\"geo-summary\" style=\"font-size:1rem;line-height:1.65;margin:0 0 1.25rem;padding:0 0 1rem;border-bottom:1px solid #e5e7eb;color:#1f2937\"\u003e\u003cstrong\u003eAIBOX-3576 RK3576 Fanless ARM Linux Mini PC\u003c\/strong\u003e is a Firefly product sold by Ai-Paipai. Key specifications — Soc: Rockchip RK3576 · Npu: 6 TOPS NPU, supports INT4\/8\/16\/FP16\/BF16\/TF32 mixed… · Ram: LPDDR4 (4GB\/8GB\/16GB optional) · Storage: eMMC (16GB\/32GB\/64GB\/128GB\/256GB optional), UFS2.0 (Only… · Ethernet: 2 × Gigabit Ethernet (1000Mbps\/RJ45). Typical applications: edge AI inference and industrial automation. Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.) is an authorized distributor providing local technical support, pre-installed SDK \/ OS images, OEM \/ ODM customization, and worldwide shipping.\u003c\/p\u003e \u003c!-- Firefly product tabs --\u003e \u003cdiv class=\"fx-tabs\" data-fx-tabs\u003e \u003cdiv class=\"fx-tablist\" role=\"tablist\"\u003e \u003cbutton class=\"fx-tab is-active\" role=\"tab\" data-fx-tab=\"0\"\u003eDescription\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"1\"\u003eWhat's Included\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"2\"\u003eSpecifications\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"3\"\u003eDocuments\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"4\"\u003eShipping Information\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"5\"\u003eWhy Buy From Ai-Paipai?\u003c\/button\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel is-active\" data-fx-panel=\"0\"\u003e \u003cdiv style=\"border:2px solid #2b6cb0;background:#f0f7ff;padding:14px 18px;margin:0 0 18px;border-radius:8px;\"\u003e \u003ch3 style=\"margin:0 0 6px;color:#2b6cb0;\"\u003e✅ Authorized Distributor — Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.)\u003c\/h3\u003e \u003cp style=\"margin:0;font-size:14px;\"\u003eThis product is supplied by an \u003cb\u003eauthorized distributor\u003c\/b\u003e of the original brand.\nWe provide \u003cb\u003elocal technical support, pre-installed SDK \/ mirror images, and OEM \/ ODM customization\u003c\/b\u003e, plus fast global shipping.\u003c\/p\u003e \u003c\/div\u003e \u003cp\u003eAIBOX-3576 is equipped with ARM Mali G52 MC3 GPU, which can provide up to 6TOPS computing power. This will enable high-level intelligent data processing, voice recognition, image analysis and other functions, effectively meeting the AI application needs of various terminal devices for edge computing.\u003c\/p\u003e \u003cul\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-3576_AIBOX-3588_AIBOX-3588S_Specification_EN.pdf?v=1750749779\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Wiki: \u003ca href=\"https:\/\/wiki.t-firefly.com\/en\/AIBOX-3576\/index.html\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e \u003cul\u003e \u003cli\u003e \u003cstrong\u003eOcta-core 64-bit AIOT Processor RK3576:\u003c\/strong\u003e RK3576 is a new octa-core 64-bit high-performance AIoT processor that adopts big.LITTLE architecture (4×A72+4×A53), uses advanced lithography technology, and has a main frequency of up to 2.2GHz. It ensures strong support for high-performance computing and multi-tasking. The Mali-G52 MC3 GPU delivers 145G FLOPS and can support efficient heterogeneous computing to meet the needs of graphics-intensive applications.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003e4K@120fps High Frame Rate Video Decoding: \u003c\/strong\u003eThis device supports 8K@30fps\/4K@120fps decoding, 4K@60fps decoding, and 4K@60fps encoding.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eStrong Network Communication Capability:\u003c\/strong\u003e The embedded PC is equipped with dual 1000Mbps Ethernet to ensure high-speed and stable network communication to meet the needs of various application scenarios.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eAll-aluminum Alloy Enclosure For Heat Dissipation:\u003c\/strong\u003e AIBOX-3576 adopts industrial-grade full metal shell and aluminum alloy structure, which is conducive to heat conduction. The grille design on the side of the top cover facilitates external airflow and efficient heat dissipation, ensuring computing performance and stability even under high temperature operating conditions.\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eHardware Overview\u003c\/strong\u003e\u003c\/h2\u003e \u003cp\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-3576.webp?v=1750749691\"\u003e\u003c\/p\u003e \u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-3576-__08_4466af1f-edf5-4e2a-9183-0db9cc47edef.jpg?v=1729654536\" alt=\"\"\u003e\u003c\/p\u003e \u003chr\u003e \u003ch2\u003e \u003c\/h2\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"1\"\u003e \u003ch3\u003eShipping list\u003c\/h3\u003e \u003cul\u003e \u003cli\u003eMain unit × 1\u003c\/li\u003e \u003cli\u003ePower adapter \/ cable (region plug on request) × 1\u003c\/li\u003e \u003cli\u003eAccessories vary by configuration — contact us for the exact included list.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"2\"\u003e \u003cdiv class=\"fx-specs\"\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eShipping list\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eAIBOX-3576*1\n12V4A Power Adapter*1\nUSB Type-C Cable\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSoc\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eRockchip RK3576\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eCpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eOcta-core 64-bit processor(4×A72+4×A53), main frequency up to 2.2GHz\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eGpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eG52 MC3@1GHz, supports OpenGL ES 1.1\/2.0\/3.2, OpenCL 2.0, Vulkan 1.1, embedded high-performance 2D acceleration hardware\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eNpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e6 TOPS NPU, supports INT4\/8\/16\/FP16\/BF16\/TF32 mixed operations\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eVpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eDecoding: 4K@120fps: H.265\/HEVC, VP9, AVS2, AV1,\n4K@60fps: H.264\/AVC\nEncoding: 4K@60fps: H.265\/HEVC, H.264\/AVC\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eRam\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eLPDDR4 (4GB\/8GB\/16GB optional)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eStorage\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eeMMC (16GB\/32GB\/64GB\/128GB\/256GB optional), UFS2.0 (Only AIBOX-3576 optional)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eStorage expansion\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 × M.2 (Expandable SATA 3.0\/PCIe NVMe SSD, supports 2242\/2260\/2280; Inside the computer, M.2 multiplexed with lower USB3.0), 1 × TF Card\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eDC 12V\/3A (DC 5.5 × 2.1 mm)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower consumption\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eNormal: 1.2W (12V\/100mA)\nMax: 7.2W (12V\/600mA)\nMin: 0.72W (12V\/6mA)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eOs\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eLinux OS (Ubuntu)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eWeight\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e≈ 500g\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEnvironment\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eOperating: -20℃~60℃, \nStorage: -20℃~70℃, \nStorage Humidity: 10%~90%RH (non-condensing)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEthernet\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 × Gigabit Ethernet (1000Mbps\/RJ45)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eOther interface\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 × Type-C (Flash), 1 × Console (Debug serial), 1 × Power button, 1 × MaskRom\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eUsb\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 × USB3.0 (Max: 1A, M.2 multiplexed with lower USB3.0)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eProduct tutorials\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSdk software and firmware files\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"3\"\u003e \u003cdiv class=\"fx-docs\"\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct tutorials\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct datasheet\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eSDK software and firmware files\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eDocument links will be replaced with the official Firefly resource URLs on request.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"4\"\u003e \u003cp\u003e\u003cb\u003eOur cooperating carriers:\u003c\/b\u003e FedEx, DHL, UPS, SF Express\u003c\/p\u003e \u003ch3\u003eDelivery Area And Cost\u003c\/h3\u003e \u003cdiv class=\"fx-scroll\"\u003e \u003ctable class=\"fx-table\"\u003e \u003cthead\u003e\u003ctr\u003e \u003cth\u003eCountry\/Region\u003c\/th\u003e \u003cth\u003e0–2kg\u003c\/th\u003e \u003cth\u003e2–3kg\u003c\/th\u003e \u003cth\u003e3–4kg\u003c\/th\u003e \u003cth\u003e4–5kg\u003c\/th\u003e \u003cth\u003e5–6kg\u003c\/th\u003e \u003cth\u003e6–7kg\u003c\/th\u003e \u003cth\u003e7–8kg\u003c\/th\u003e \u003cth\u003e8–9kg\u003c\/th\u003e \u003cth\u003e9–10kg\u003c\/th\u003e \u003c\/tr\u003e\u003c\/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd\u003eJapan, Taiwan, Hong Kong, Macau\u003c\/td\u003e \u003ctd\u003e$15\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSingapore, Thailand, Malaysia\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eIndonesia, Philippines\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003ctd\u003e$70\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSouth Korea\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eUnited States, Australia, New Zealand, Canada, UK, and most of Western Europe\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$75\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$105\u003c\/td\u003e \u003ctd\u003e$115\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eOther regions (Eastern Europe, Middle East, Latin America, etc.)\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$110\u003c\/td\u003e \u003ctd\u003e$125\u003c\/td\u003e \u003ctd\u003e$135\u003c\/td\u003e \u003ctd\u003e$150\u003c\/td\u003e \u003ctd\u003e$165\u003c\/td\u003e \u003c\/tr\u003e \u003c\/tbody\u003e \u003c\/table\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eShipping time is for reference only; the actual situation shall prevail.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"5\"\u003e\n Why Buy From Ai-Paipai? \u003cul\u003e \u003cli\u003e \u003cb\u003eAuthorized \u0026amp; Genuine\u003c\/b\u003e — sourced directly from brand-approved channels.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eLocal Engineering Support\u003c\/b\u003e — datasheets, SDKs, and pre-flashed images in English and Chinese.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOEM \/ ODM \u0026amp; FPGA Customization\u003c\/b\u003e — tailor specs, enclosures, and BSP for your project.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOne-Stop Sourcing\u003c\/b\u003e — Firefly + youyeetoo + our own FPGA \/ edge lineup in one store.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cstyle\u003e.fx-tabs{margin:24px 0;border:1px solid #e5e7eb;border-radius:10px;overflow:hidden;background:#fff}.fx-tablist{display:flex;flex-wrap:wrap;gap:0;border-bottom:1px solid #e5e7eb;background:#f8fafc}.fx-tab{flex:1 1 auto;min-width:120px;padding:14px 16px;border:0;background:transparent;cursor:pointer;font:600 14px\/1.3 inherit;color:#475569;border-bottom:3px solid transparent;transition:.18s}.fx-tab:hover{color:#0f172a;background:#eef2f7}.fx-tab.is-active{color:#0f172a;border-bottom-color:#2563eb;background:#fff}.fx-panel{display:none;padding:22px 24px}.fx-panel.is-active{display:block}.fx-panel h3{font-size:16px;margin:22px 0 8px;font-weight:700}.fx-panel h3:first-child{margin-top:0}.fx-panel p{margin:10px 0;line-height:1.65}.fx-panel ul{margin:10px 0;padding-left:22px}.fx-panel li{margin:6px 0;line-height:1.6}.fx-auth{background:#f0fdf4;border:1px solid #bbf7d0;border-radius:8px;padding:12px 14px;margin:0 0 16px;font-size:14px;line-height:1.6}.fx-specs{border-top:1px solid #eef2f7}.fx-spec{display:grid;grid-template-columns:230px 1fr;gap:16px;padding:12px 4px;border-bottom:1px solid #eef2f7}.fx-k{font-weight:700;color:#334155}.fx-v{color:#475569}.fx-docs{display:flex;flex-direction:column;gap:10px}.fx-doc{display:flex;justify-content:space-between;align-items:center;gap:12px;padding:12px 14px;border:1px solid #e5e7eb;border-radius:8px}.fx-doc a{color:#2563eb;font-weight:700;text-decoration:none}.fx-doc a:hover{text-decoration:underline}.fx-scroll{overflow-x:auto}.fx-table{border-collapse:collapse;width:100%;min-width:760px;font-size:13px}.fx-table th,.fx-table td{border:1px solid #e5e7eb;padding:8px 10px;text-align:left}.fx-table th{background:#f8fafc;font-weight:700}.fx-note{color:#64748b;font-size:13px;margin-top:12px}\n @media (max-width:749px){.fx-spec{grid-template-columns:1fr;gap:4px}.fx-tab{min-width:50%;flex:1 1 50%}.fx-panel{padding:16px}} \u003c\/style\u003e \u003cscript\u003e\n (function () {\n var roots = document.querySelectorAll('[data-fx-tabs]');\n roots.forEach(function (root) {\n var tabs = root.querySelectorAll('[data-fx-tab]');\n var panels = root.querySelectorAll('[data-fx-panel]');\n tabs.forEach(function (t) {\n t.addEventListener('click', function () {\n var i = t.getAttribute('data-fx-tab');\n tabs.forEach(function (x) { x.classList.toggle('is-active', x === t); });\n panels.forEach(function (p) { p.classList.toggle('is-active', p.getAttribute('data-fx-panel') === i); });\n });\n });\n });\n })(); \u003c\/script\u003e","brand":"Firefly","offers":[{"title":"4G RAM+32G ROM \/ Standard","offer_id":48422541426946,"sku":"firefly-aibox-3576-large-model-ai-box-41541915803732","price":249.0,"currency_code":"USD","in_stock":true},{"title":"4G RAM+32G ROM \/ Deepseek Deployed","offer_id":48422541459714,"sku":"firefly-aibox-3576-large-model-ai-box-41892667129940","price":279.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+64G ROM \/ Standard","offer_id":48422541492482,"sku":"firefly-aibox-3576-large-model-ai-box-41541915836500","price":339.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+64G ROM \/ Deepseek Deployed","offer_id":48422541525250,"sku":"firefly-aibox-3576-large-model-ai-box-41892667162708","price":379.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0837\/5953\/0242\/files\/AIBox-3576-800800_3_5be0f5f1-31a0-4661-8d9a-4adb8a1e8b1e.jpg?v=1788244384"},{"product_id":"aibox-orinnano-67tops-ai-big-model-of-edge-computing-jetson-module-nvidia","title":"AIBOX-OrinNano Jetson Orin Nano Embedded PC","description":"\u003cp class=\"geo-summary\" style=\"font-size:1rem;line-height:1.65;margin:0 0 1.25rem;padding:0 0 1rem;border-bottom:1px solid #e5e7eb;color:#1f2937\"\u003e\u003cstrong\u003eAIBOX-OrinNano Jetson Orin Nano Embedded PC\u003c\/strong\u003e is a Firefly product sold by Ai-Paipai. Key specifications — Cpu: Hexa-core 64-bit ARM Cortex-A78AE v8.2 processor, up to… · Ai performance: 67 TOPS · Traditional network architectures: Traditional network architectures such as CNN, RNN, and… · Video output: 1×HDMI 2.1 (4K@60fps) · Usb: 2 × USB 3.0 (Max: 1A). Typical applications: edge AI inference, machine vision and industrial automation. Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.) is an authorized distributor providing local technical support, pre-installed SDK \/ OS images, OEM \/ ODM customization, and worldwide shipping.\u003c\/p\u003e \u003c!-- Firefly product tabs --\u003e \u003cdiv class=\"fx-tabs\" data-fx-tabs\u003e \u003cdiv class=\"fx-tablist\" role=\"tablist\"\u003e \u003cbutton class=\"fx-tab is-active\" role=\"tab\" data-fx-tab=\"0\"\u003eDescription\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"1\"\u003eWhat's Included\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"2\"\u003eSpecifications\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"3\"\u003eDocuments\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"4\"\u003eShipping Information\u003c\/button\u003e \u003cbutton class=\"fx-tab\" role=\"tab\" data-fx-tab=\"5\"\u003eWhy Buy From Ai-Paipai?\u003c\/button\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel is-active\" data-fx-panel=\"0\"\u003e \u003cdiv style=\"border:2px solid #2b6cb0;background:#f0f7ff;padding:14px 18px;margin:0 0 18px;border-radius:8px;\"\u003e \u003ch3 style=\"margin:0 0 6px;color:#2b6cb0;\"\u003e✅ Authorized Distributor — Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.)\u003c\/h3\u003e \u003cp style=\"margin:0;font-size:14px;\"\u003eThis product is supplied by an \u003cb\u003eauthorized distributor\u003c\/b\u003e of the original brand.\nWe provide \u003cb\u003elocal technical support, pre-installed SDK \/ mirror images, and OEM \/ ODM customization\u003c\/b\u003e, plus fast global shipping.\u003c\/p\u003e \u003c\/div\u003e \u003cp\u003eAIBOX-OrinNano is equipped with NVIDIA's original Jetson Orin Nano core module (8GB RAM version), providing up to 67 TOPS of computing power, supporting private deployment of mainstream AI models such as Transformer and ROS robot models, thereby realizing larger and more complex deep neural networks, and realizing visual development tasks such as object recognition, target detection and tracking, and speech recognition, meeting higher-level AI application scenario requirements.\u003c\/p\u003e \u003cul\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-OrinNano_AIBOX-OrinNX_Specification_EN.pdf?v=1749620262\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Wiki: \u003ca href=\"https:\/\/wiki.t-firefly.com\/en\/AIBOX-Orin-Nano\/index.html\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eApplication Cases \u003c\/strong\u003e\u003c\/h2\u003e \u003cul\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003ca href=\"https:\/\/www.firefly.store\/blogs\/technical-case\/aibox-application-case-background-removal-via-u-net\"\u003e\u003cstrong\u003eBackground Removal via U²-Net\u003c\/strong\u003e\u003c\/a\u003e\u003c\/li\u003e \u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003e\u003ca href=\"https:\/\/www.firefly.store\/blogs\/news\/monocular-depth-estimation-aibox-application\"\u003eMonocular Depth Estimation\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e \u003cul\u003e \u003cli\u003e \u003cstrong\u003eHigh-performance Edge Computing Module: \u003c\/strong\u003eThe NVIDIA Jetson Orin Nano edge computing module (8GB version) is equipped with a six-core ARM CPU and a 1024-core NVIDIA Ampere architecture GPU (including 32 Tensor Cores), which can run multiple AI application pipelines simultaneously and provide powerful inference performance.\u003cstrong\u003e\u003cbr\u003e\u003c\/strong\u003e \u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eMultiple Deep Learning Frameworks: \u003c\/strong\u003eIt supports a variety of cuDNN-accelerated deep learning frameworks, including PaddlePaddle, PyTorch, TensorFlow, MATLAB, MxNet, Caffe2, Chainer, Keras, etc., as well as custom operator development, and supports Docker containerization technology.\u003cbr\u003e \u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eAluminum Alloy Enclosure With Efficient Heat Dissipation: \u003c\/strong\u003eAIBOX adopts an industrial-grade all-metal shell and an aluminum alloy structure with good thermal conductivity. The grille design on the side of the top cover is conducive to external airflow and efficient heat dissipation, ensuring computing performance and stability even in high-temperature operating environments.\u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eApplication\u003c\/strong\u003e\u003c\/h2\u003e \u003cul\u003e \u003cli\u003e \u003cstrong\u003eAI Software Stack And Ecosystem:\u003c\/strong\u003e NVIDIA JetPack, Isaac ROS, and reference AI workflows seamlessly integrate cutting-edge technologies into your products without expensive in-house AI resources. Experience end-to-end acceleration of AI applications and get to market faster using the same powerful technology that drives data center and cloud deployments.\u003c\/li\u003e \u003cli\u003e \u003cstrong\u003eThe Private Deployment Of Large Models:\u003c\/strong\u003e Large language model: supports the Ollamalocal large model deployment framework and private deployment of ultra-large-scale parameterized models: Llama3, Phi-3 Mini. Vision model: supports EfficientVIT, NanoOWL, NanoSAM, SAM, TAM. AI painting: supports ComfyUIgraphical deployment framework and private deployment of Flux, and a stable Diffusion image generation model in the AIGC field.\u003cbr\u003e \u003c\/li\u003e \u003c\/ul\u003e \u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eHardware Overview\u003c\/strong\u003e\u003c\/h2\u003e \u003cp\u003e\u003cstrong\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/ORINAIBOX.webp?v=1751269631\"\u003e\u003c\/strong\u003e\u003c\/p\u003e \u003chr\u003e \u003ch2\u003e \u003c\/h2\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"1\"\u003e \u003ch3\u003eShipping list\u003c\/h3\u003e \u003cul\u003e \u003cli\u003eMain unit × 1\u003c\/li\u003e \u003cli\u003ePower adapter \/ cable (region plug on request) × 1\u003c\/li\u003e \u003cli\u003eAccessories vary by configuration — contact us for the exact included list.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"2\"\u003e \u003cdiv class=\"fx-specs\"\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eShipping list\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eAIBOX-OrinNano*1\n12V3A Power Adapter*1\nType-C 2.0 USB Cable*1\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eAi performance\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e67 TOPS\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eTraditional network architectures\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eTraditional network architectures such as CNN, RNN, and LSTM; a variety of deep learning frameworks include TensorFlow, PyTorch, MXNet, PaddlePaddle, ONNX, and Darknet; custom operator development.\nDocker container management technology facilitates easy image deployment.\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eAi software stack\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eNVIDIA Jetson Orin offers unparalleled AI computing, large unified memory, and comprehensive software stacks, delivering superior energy efficiency to drive the latest generative AI applications. It’s capable of fast inference for any generative AI models powered by the transformer architecture, providing superior edge performance on MLPerf.\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eLarge model\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eRobotic models: ROS models.\nLarge language models: The private deployment of ultra-large-scale parameter models under the Transformer architecture, such as LLaMa2, ChatGLM, and Qwen.\nVision models: ViT, Grounding DINO, and SAM.\nAI painting: Stable Diffusion V1.5 image generation model in the AIGC field.\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eCpu\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eHexa-core 64-bit ARM Cortex-A78AE v8.2 processor, up to 1.7GHz\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eDC 12V (DC 5.5 x 2.1mm) \u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003ePower consumption\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eNormal: 7.2W (12V\/600mA)\nMax: 18W (12V\/1500mA)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eVideo output\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1×HDMI 2.1 (4K@60fps)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eOs\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eThe Jetson system, based on Ubuntu 22.04, offers a comprehensive desktop Linux environment with accelerated graphics, supporting libraries such as NVIDIA CUDA, TensorRT, and CuDNN.\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eDimension\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e93.4 mm x 93.4 mm x 50 mm\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eWeight\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e≈ 500g\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEnvironment\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eOperating temperature: -20℃~60℃\nStorage temperature: -20℃~70℃\nStorage Humidity: 10%~90%RH (non-condensing)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eWatchdog\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eSupport external watchdog\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eEthernet\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 × Gigabit Ethernet (1000Mbps \/ RJ45)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eUsb\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e2 × USB 3.0 (Max: 1A)\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eOther\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003e1 × Type-C (USB 2.0 OTG)\n1 × Console (debug serial port)\n1 × Recovery\n1 × power button\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eProduct tutorials\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-spec\"\u003e \u003cdiv class=\"fx-k\"\u003eSdk software and firmware files\u003c\/div\u003e \u003cdiv class=\"fx-v\"\u003eClick Here\u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"3\"\u003e \u003cdiv class=\"fx-docs\"\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct tutorials\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eProduct datasheet\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003cdiv class=\"fx-doc\"\u003e \u003cspan\u003eSDK software and firmware files\u003c\/span\u003e\u003ca href=\"#\" target=\"_blank\" rel=\"noopener\"\u003eClick Here\u003c\/a\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eDocument links will be replaced with the official Firefly resource URLs on request.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"4\"\u003e \u003cp\u003e\u003cb\u003eOur cooperating carriers:\u003c\/b\u003e FedEx, DHL, UPS, SF Express\u003c\/p\u003e \u003ch3\u003eDelivery Area And Cost\u003c\/h3\u003e \u003cdiv class=\"fx-scroll\"\u003e \u003ctable class=\"fx-table\"\u003e \u003cthead\u003e\u003ctr\u003e \u003cth\u003eCountry\/Region\u003c\/th\u003e \u003cth\u003e0–2kg\u003c\/th\u003e \u003cth\u003e2–3kg\u003c\/th\u003e \u003cth\u003e3–4kg\u003c\/th\u003e \u003cth\u003e4–5kg\u003c\/th\u003e \u003cth\u003e5–6kg\u003c\/th\u003e \u003cth\u003e6–7kg\u003c\/th\u003e \u003cth\u003e7–8kg\u003c\/th\u003e \u003cth\u003e8–9kg\u003c\/th\u003e \u003cth\u003e9–10kg\u003c\/th\u003e \u003c\/tr\u003e\u003c\/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd\u003eJapan, Taiwan, Hong Kong, Macau\u003c\/td\u003e \u003ctd\u003e$15\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSingapore, Thailand, Malaysia\u003c\/td\u003e \u003ctd\u003e$20\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eIndonesia, Philippines\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$40\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$60\u003c\/td\u003e \u003ctd\u003e$70\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eSouth Korea\u003c\/td\u003e \u003ctd\u003e$25\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$35\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eUnited States, Australia, New Zealand, Canada, UK, and most of Western Europe\u003c\/td\u003e \u003ctd\u003e$30\u003c\/td\u003e \u003ctd\u003e$45\u003c\/td\u003e \u003ctd\u003e$55\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$75\u003c\/td\u003e \u003ctd\u003e$85\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$105\u003c\/td\u003e \u003ctd\u003e$115\u003c\/td\u003e \u003c\/tr\u003e \u003ctr\u003e \u003ctd\u003eOther regions (Eastern Europe, Middle East, Latin America, etc.)\u003c\/td\u003e \u003ctd\u003e$50\u003c\/td\u003e \u003ctd\u003e$65\u003c\/td\u003e \u003ctd\u003e$80\u003c\/td\u003e \u003ctd\u003e$95\u003c\/td\u003e \u003ctd\u003e$110\u003c\/td\u003e \u003ctd\u003e$125\u003c\/td\u003e \u003ctd\u003e$135\u003c\/td\u003e \u003ctd\u003e$150\u003c\/td\u003e \u003ctd\u003e$165\u003c\/td\u003e \u003c\/tr\u003e \u003c\/tbody\u003e \u003c\/table\u003e \u003c\/div\u003e \u003cp class=\"fx-note\"\u003eShipping time is for reference only; the actual situation shall prevail.\u003c\/p\u003e \u003c\/div\u003e \u003cdiv class=\"fx-panel\" data-fx-panel=\"5\"\u003e\n Why Buy From Ai-Paipai? \u003cul\u003e \u003cli\u003e \u003cb\u003eAuthorized \u0026amp; Genuine\u003c\/b\u003e — sourced directly from brand-approved channels.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eLocal Engineering Support\u003c\/b\u003e — datasheets, SDKs, and pre-flashed images in English and Chinese.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOEM \/ ODM \u0026amp; FPGA Customization\u003c\/b\u003e — tailor specs, enclosures, and BSP for your project.\u003c\/li\u003e \u003cli\u003e \u003cb\u003eOne-Stop Sourcing\u003c\/b\u003e — Firefly + youyeetoo + our own FPGA \/ edge lineup in one store.\u003c\/li\u003e \u003c\/ul\u003e \u003c\/div\u003e \u003c\/div\u003e \u003cstyle\u003e.fx-tabs{margin:24px 0;border:1px solid #e5e7eb;border-radius:10px;overflow:hidden;background:#fff}.fx-tablist{display:flex;flex-wrap:wrap;gap:0;border-bottom:1px solid #e5e7eb;background:#f8fafc}.fx-tab{flex:1 1 auto;min-width:120px;padding:14px 16px;border:0;background:transparent;cursor:pointer;font:600 14px\/1.3 inherit;color:#475569;border-bottom:3px solid transparent;transition:.18s}.fx-tab:hover{color:#0f172a;background:#eef2f7}.fx-tab.is-active{color:#0f172a;border-bottom-color:#2563eb;background:#fff}.fx-panel{display:none;padding:22px 24px}.fx-panel.is-active{display:block}.fx-panel h3{font-size:16px;margin:22px 0 8px;font-weight:700}.fx-panel h3:first-child{margin-top:0}.fx-panel p{margin:10px 0;line-height:1.65}.fx-panel ul{margin:10px 0;padding-left:22px}.fx-panel li{margin:6px 0;line-height:1.6}.fx-auth{background:#f0fdf4;border:1px solid #bbf7d0;border-radius:8px;padding:12px 14px;margin:0 0 16px;font-size:14px;line-height:1.6}.fx-specs{border-top:1px solid #eef2f7}.fx-spec{display:grid;grid-template-columns:230px 1fr;gap:16px;padding:12px 4px;border-bottom:1px solid #eef2f7}.fx-k{font-weight:700;color:#334155}.fx-v{color:#475569}.fx-docs{display:flex;flex-direction:column;gap:10px}.fx-doc{display:flex;justify-content:space-between;align-items:center;gap:12px;padding:12px 14px;border:1px solid #e5e7eb;border-radius:8px}.fx-doc a{color:#2563eb;font-weight:700;text-decoration:none}.fx-doc a:hover{text-decoration:underline}.fx-scroll{overflow-x:auto}.fx-table{border-collapse:collapse;width:100%;min-width:760px;font-size:13px}.fx-table th,.fx-table td{border:1px solid #e5e7eb;padding:8px 10px;text-align:left}.fx-table th{background:#f8fafc;font-weight:700}.fx-note{color:#64748b;font-size:13px;margin-top:12px}\n @media (max-width:749px){.fx-spec{grid-template-columns:1fr;gap:4px}.fx-tab{min-width:50%;flex:1 1 50%}.fx-panel{padding:16px}} \u003c\/style\u003e \u003cscript\u003e\n (function () {\n var roots = document.querySelectorAll('[data-fx-tabs]');\n roots.forEach(function (root) {\n var tabs = root.querySelectorAll('[data-fx-tab]');\n var panels = root.querySelectorAll('[data-fx-panel]');\n tabs.forEach(function (t) {\n t.addEventListener('click', function () {\n var i = t.getAttribute('data-fx-tab');\n tabs.forEach(function (x) { x.classList.toggle('is-active', x === t); });\n panels.forEach(function (p) { p.classList.toggle('is-active', p.getAttribute('data-fx-panel') === i); });\n });\n });\n });\n })(); \u003c\/script\u003e","brand":"Firefly","offers":[{"title":"8G RAM+128G SSD \/ Standard without Wifi","offer_id":48422541623554,"sku":"firefly-aibox-orinnano-67tops-ai-big-model-of-edge-computing-jetson-module-nvidia-42231535829076","price":709.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+128G SSD \/ Deepseek Deployed without Wifi","offer_id":48422541656322,"sku":"firefly-aibox-orinnano-67tops-ai-big-model-of-edge-computing-jetson-module-nvidia-42231535861844","price":729.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+256G SSD \/ Standard without Wifi","offer_id":48422541689090,"sku":"firefly-aibox-orinnano-67tops-ai-big-model-of-edge-computing-jetson-module-nvidia-45300305756244","price":819.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+256G SSD \/ Deepseek Deployed without Wifi","offer_id":48422541721858,"sku":"firefly-aibox-orinnano-67tops-ai-big-model-of-edge-computing-jetson-module-nvidia-45300305789012","price":829.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0837\/5953\/0242\/files\/800800-1_03c4016b-006a-45e0-9ae7-4875f2eb8425.jpg?v=1788244387"},{"product_id":"aibox-pro-kit","title":"AIBOX PRO KIT Dual-AI Matrix Edge Computer","description":"\u003cp\u003e\u003cstrong\u003eAIBOX PRO KIT\u003c\/strong\u003e is a dual-AI matrix edge computer built for on-device large model deployment. It pairs a modular Rockchip host SoC with one or two independent M.2 AI accelerator modules, so compute power and memory can be scaled by swapping modules instead of redesigning the whole system.\u003c\/p\u003e\n\n\u003cp\u003eInstead of a fixed-specification AI box, the PRO KIT uses a heterogeneous modular architecture — a main controller plus an independent AI coprocessor — supporting LLM, VLM and AI Agent workloads while remaining compatible with traditional CNN and RNN algorithms. It integrates CAN-FD and RS485 industrial interfaces, making it suitable for both general AI and industrial intelligence deployment.\u003c\/p\u003e\n\n\u003ch3\u003eKey features\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eDual-core architecture\u003c\/strong\u003e — host SoC module plus an independent AI coprocessor module\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003e2 × M.2 M-KEY accelerator slots\u003c\/strong\u003e — accepts RK1828, HOUMO LQ50, DeepX DX-M1 and other 2260\/2280 M.2 modules\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eRuns LLMs up to 7B smoothly\u003c\/strong\u003e with RK1828 (5GB DRAM, 20 TOPS INT8); \u003cstrong\u003eup to 35B with LQ50\u003c\/strong\u003e (48GB LPDDR5, 160 TOPS INT8)\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003e8K video\u003c\/strong\u003e — 8K@30fps H.265\/H.264 encoding and 8K@60fps H.265 decoding with RK3588 host\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eOnboard SATA 3.0, PCIe NVMe, TF card\u003c\/strong\u003e storage expansion and dual Gigabit Ethernet\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eIndustrial I\/O\u003c\/strong\u003e — RS485, CAN-FD, opto-isolated DI\/DO, 9–36V wide voltage input, −20°C to 60°C operation\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eMillisecond-level low latency\u003c\/strong\u003e with rich expansion and full development materials\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eSpecifications\u003c\/h3\u003e\n\u003ctable\u003e\n  \u003ctbody\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eHost module\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003eOptional modules as follows:\u003cbr\u003eRK3588 module (Core-3588JD4): LPDDR4\/LPDDR4x (4\/8\/16\/32GB) + eMMC (32\/64\/128\/256GB), 6 TOPS (INT8)\u003cbr\u003eRK3576 module (Core-3576JD4): LPDDR4\/LPDDR4x (2\/4\/8\/16GB) + eMMC (16\/32\/64\/128\/256GB), 6 TOPS (INT8)\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eVideo encoding\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003eRK3588: 8K@30fps H.265\/H.264\u003cbr\u003eRK3576: 4K@60fps H.265\/H.264\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eVideo decoding\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003eRK3588: 8K@60fps H.265\/VP9\/AVS2, 8K@30fps H.264\/AVC\/MVC, 4K@60fps AV1, 1080P@60fps MPEG-2\/-1\/VC-1\/VP8\u003cbr\u003eRK3576: 8K@30fps H.265\/VP9\/AVS2\/AV1, 4K@120fps H.265\/VP9\/AVS2\/AV1, 4K@60fps H.264\/AVC\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\n\u003cstrong\u003eAccelerator expansion\u003c\/strong\u003e\u003cbr\u003e(slave module)\u003c\/td\u003e\n\u003ctd\u003e2 × M.2 M-KEY (supports 2260\/2280 accelerator cards \u0026amp; other M.2 modules, inside the device)\u003cbr\u003e* Users can install any brand M.2 M-KEY accelerators; standard equipped with RK1828 \/ HOUMO LQ50 modules\u003cbr\u003e○ RK1828: onboard 5GB DRAM, 20 TOPS (INT8), runs LLMs up to 7B smoothly\u003cbr\u003e○ LQ50: 48GB LPDDR5, 160 TOPS (INT8), runs LLMs up to 35B smoothly\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eStorage expansion\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003e1 × M.2 M-KEY (expandable with PCIe 2.0 x1 NVMe 2280 SSD; unavailable when Core-3576JD4 serves as the host module)\u003cbr\u003e1 × SATA 3.0 (expandable with SATA 3.0 SSD; unavailable when Core-3576JD4 serves as the host module)\u003cbr\u003e1 × TF card\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003ePower\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003eDC 12V\/7A (5.5×2.1mm, supports 9V–36V wide voltage input)\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eAccelerator power\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003e2 × 12V (2 pcs 4Pin-1.25mm wafer sockets)\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003ePower consumption\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003eRK3588 + 1 × RK1828: Normal 9.6W (12V\/800mA), Max 28.8W (12V\/2400mA), Min (sleep) 0.72W (12V\/60mA)\u003cbr\u003eRK3588 + 2 × RK1828: Normal 15.6W (12V\/1300mA), Max 42W (12V\/3500mA), Min (sleep) 0.72W (12V\/60mA)\u003cbr\u003eRK3588 + 1 × LQ50: Normal 8.4W (12V\/700mA), Max 45.6W (12V\/3800mA), Min (sleep) 0.84W (12V\/70mA)\u003cbr\u003eRK3588 + 1 × LQ50 DUO: Normal 12W (12V\/1000mA), Max 63.6W (12V\/5300mA), Min (sleep) 0.84W (12V\/70mA)\u003cbr\u003eRK3576 + 1 × RK1828: Normal 8.4W (12V\/700mA), Max 28.8W (12V\/2400mA), Min (sleep) 1.2W (12V\/100mA)\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eOS\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003eLinux\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eDimensions\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003e148.0mm × 106.0mm × 36.4mm\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eEnvironment\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003eOperating temperature: −20°C to 60°C; storage temperature: −20°C to 70°C; storage humidity: 10%–90% RH (non-condensing)\u003c\/td\u003e\n\u003c\/tr\u003e\n  \u003c\/tbody\u003e\n\u003c\/table\u003e\n\n\u003ch3\u003eInterface specifications\u003c\/h3\u003e\n\u003ctable\u003e\n  \u003ctbody\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eInternet\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003e2 × Gigabit Ethernet (1000Mbps\/RJ45)\u003cbr\u003eWi-Fi \u0026amp; Bluetooth: dual-band 2.4GHz\/5GHz Wi-Fi and Bluetooth 5.2 (expandable via M.2 E-KEY; unavailable with Core-3576JD4 host module)\u003cbr\u003e4G: expandable via Mini PCIe  |  5G: expandable via M.2 B-KEY\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eVideo output\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003e1 × HDMI 2.1 (up to 4K@60Hz)\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eAudio input\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003e1 × Line In (3.5mm audio jack)\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eAudio output\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003e1 × Line Out (3.5mm audio jack)\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eUSB\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003e2 × USB 3.0 (max 1A), 2 × USB 2.0 HOST (4Pin-2mm), 1 × Type-C (USB 2.0 OTG), 1 × Type-C (debug)\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eButton\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003e1 × power key, 1 × upgrade key, 1 × reset key\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eOther interfaces\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003e1 × SIM card, 1 × SATA power (4Pin-5.08mm), 2 × FAN (4Pin-1.25mm), 1 × Phoenix terminal block (8Pin-3.5mm): 1 × RS485, 1 × CAN-FD, 2 × opto-isolated DI\/DO\u003c\/td\u003e\n\u003c\/tr\u003e\n  \u003c\/tbody\u003e\n\u003c\/table\u003e\n\n\u003ch3\u003eAvailable configurations\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eRK3588 (8GB+64GB) + RK1828 ×1\u003c\/strong\u003e — entry dual-AI kit, 20 TOPS INT8 accelerator, runs LLMs up to 7B\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eRK3588 (8GB+64GB) + RK1828 ×2\u003c\/strong\u003e — dual accelerator configuration for higher throughput and parallel model serving\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003eNeed RK3576, LQ50, DX-M1 or a custom module combination? Contact us at \u003ca href=\"mailto:lixu@ai-paipai.com\"\u003elixu@ai-paipai.com\u003c\/a\u003e for a configuration quote.\u003c\/p\u003e\n\n\u003ch3\u003eTypical applications\u003c\/h3\u003e\n\u003cp\u003eRobotics, edge AI computing, industrial automation, intelligent security, autonomous driving, smart cities, traffic management, home storage and retail automation.\u003c\/p\u003e\n\n\u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/1_01_2a6e87af-5b11-473c-a285-f6837ef2f857.jpg?v=1788921557\" alt=\"AIBOX PRO KIT - Firefly dual-AI matrix edge computer\" loading=\"lazy\"\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/1_02_f85a1a87-7092-4727-977e-b9a9943daa7a.jpg?v=1788921545\" alt=\"AIBOX PRO KIT - Firefly dual-AI matrix edge computer\" loading=\"lazy\"\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/1_03_33cafbe2-43f9-4dd8-9ddc-d23411c545d2.jpg?v=1788921551\" alt=\"AIBOX PRO KIT - Firefly dual-AI matrix edge computer\" loading=\"lazy\"\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/1_04_0daea2f3-4a1b-420b-970f-2537450930bf.jpg?v=1788921554\" alt=\"AIBOX PRO KIT - Firefly dual-AI matrix edge computer\" loading=\"lazy\"\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/1_05_fe34ee8e-3830-4c30-9b02-ee93f11dd8c7.jpg?v=1788921545\" alt=\"AIBOX PRO KIT - Firefly dual-AI matrix edge computer\" loading=\"lazy\"\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/1_06_73aa024f-f7b8-4b55-bbec-dc508b75b51b.jpg?v=1788921539\" alt=\"AIBOX PRO KIT - Firefly dual-AI matrix edge computer\" loading=\"lazy\"\u003e\u003c\/p\u003e\n\n\u003cp\u003e\u003cem\u003eAi-Paipai is an authorized Firefly distributor providing engineering support, configuration guidance and worldwide express shipping from Shenzhen.\u003c\/em\u003e\u003c\/p\u003e","brand":"Firefly","offers":[{"title":"RK3588 (8GB+64GB) + RK1828 ×1","offer_id":48478148591874,"sku":null,"price":859.0,"currency_code":"USD","in_stock":true},{"title":"RK3588 (8GB+64GB) + RK1828 ×2","offer_id":48478148624642,"sku":null,"price":1109.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0837\/5953\/0242\/files\/1_1_2142616b-5682-4d0a-9cda-c776a3ead122.jpg?v=1789127215"}],"url":"https:\/\/ai-paipai.store\/collections\/firefly-aibox.oembed","provider":"Ai-Paipai","version":"1.0","type":"link"}