Skip to product information
1 of 3

Firefly

iCore-3576Q AIOT System on Module RK3576

iCore-3576Q AIOT System on Module RK3576

Regular price $149.00 USD
Regular price Sale price $149.00 USD
Sale Sold out
Shipping calculated at checkout.
Configuration
Quantity

iCore-3576Q AIOT System on Module RK3576 is a Firefly product sold by Ai-Paipai. Key specifications — Soc: Rockchip RK3576 · Ai performance: Support the privatization deployment of… · Storage: eMMC (16GB/32GB/64GB/128GB/256GB optional), UFS2.0… · Video output: 1 × HDMI2.1(4096×2160@120Hz)/eDP1.3(4096×2160@60Hz,… · Interface type: BTB (2 × BTB Socket(80Pin) + 2 × BTB Socket(100Pin)). Typical applications: edge AI inference, machine vision and IoT gateway deployments. 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.

✅ Authorized Distributor — Ai-Paipai (Shenzhen AiPaipai Intelligent Technology Co., Ltd.)

This product is supplied by an authorized distributor of the original brand. We provide local technical support, pre-installed SDK / mirror images, and OEM / ODM customization, plus fast global shipping.

The Rockchip RK3576-powered iCore-3576Q is an octa-core 64-bit AIoT processor with an ARM Mali G52 MC3 GPU and a 6 TOPS NPU, enabling high-performance AI computing and low power consumption. It supports 4K@120fps decoding, 4K@60fps encoding, and private large model deployment, ideal for industrial AI applications. Featuring industrial-grade stability, a BTB interface, and external watchdog support, it ensures reliable 4K@120fps display output for embedded and edge computing solutions.

Feature

  • High-performance AIOT Processor RK3576: Rockchip RK3576 AIoT Processor – An octa-core 64-bit powerhouse with big.LITTLE architecture (4×A72 + 4×A53 @2.2GHz), advanced lithography, and high-performance computing. Equipped with a Mali-G52 MC3 GPU (145G FLOPS) for efficient graphics processing, it delivers robust multitasking and AI acceleration for embedded and edge AI applications.
  • The Private Deployment of Large Models: Large language models such as LLaMa2, ChatGLM, and Qwen. Traditional network architectures, Docker container.
  • 4K@120fps High Frame Rate Video Decoding: Supports 4K@120fps decoding (VP9, AVS2, AV1), 4K@60fps decoding (H.264/AVC), 4K@60fps encoding (H.264/AVC), and provides HDMI 2.1 (4K@120fps)/eDP1.3 (4K@60fps), DP1.4 (4K@120fps).
  • UFS 2.0 with A Data Read Speed of 12Gbps: The device supports UFS 2.0 / HS-G3 (12 Gbps), ensuring efficient data storage and access. PCIe NVMe / SATA SSD expansion provides fast data read and write speeds, allowing the device to be easily expanded to TB-level storage capacity.

Hardware Overview


Shipping list

  • Main unit × 1
  • Power adapter / cable (region plug on request) × 1
  • Accessories vary by configuration — contact us for the exact included list.
Ai performance
Support the privatization deployment of ultra-large-scale parametric models under the Transformer architecture, such as Gemma-2B, ChatGLM3-6B, Qwen-1.8B, Phi-3-3.8B, and other large language models. 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. Support Docker container management technology. It supports the real-time object detection algorithm YOLO (You Only Look Once), which is fast and real-time compared with traditional object detection methods, and can accurately identify and locate multiple target objects in images or videos, powering AI applications.
Soc
Rockchip RK3576
Cpu
Octa-core 64-bit processor (4×A72 + 4×A53) with a maximum frequency of 2.2GHz
Gpu
G52 MC3@1GHz, support OpenGL ES 1.1/2.0/3.2, OpenCL 2.0, Vulkan 1.1, embedded with high-performance 2D acceleration hardware
Npu
6 TOPS NPU, It supports INT4/INT8/INT16/FP16/BF16/TF32 operations, supports dual-core collaborative or independent work, and supports multi-task and multi-scene parallelism
Storage
eMMC (16GB/32GB/64GB/128GB/256GB optional), UFS2.0 (Optional)
Pcie
1 × PCIe 2.1/SATA 3.1/USB 3.2 Gen1 Combo interfaces 1 × PCIe 2.1/SATA 3.1 Combo interfaces
Sata
1 × PCIe 2.1/SATA 3.1/USB 3.2 Gen1 Combo interfaces 1 × PCIe 2.1/SATA 3.1 Combo interfaces
Power
5.0V (voltage tolerance ± 5%)
Power consumption
Max: 4.5W(5V/900mA) Normal: 0.5W(5V/100mA) Min: 0.045W(5V/9mA)
Video output
1 × HDMI2.1(4096×2160@120Hz)/eDP1.3(4096×2160@60Hz, supports 1Lane/2Lane/4Lane modes) 1 × DP1.4 (4096×2160@120Hz) 1 × EBC Output interface (support E-ink EPD (Electronic Paper Display), 2560×1920) 1 × MIPI_DCPHY_TX (Supports V2.0 version and 0/1/2/3 Lane mode; C-PHY supports V1.1 version and 0/1/2 Trio mode; 2560×1600@60Hz) 1 × LCDC TX (Supports parallel 24 bit RGB mode) 1920×1080@60Hz 16 bit BT1120 mode 1920×1080@60Hz 8-bit BT656 mode 720×576@60Hz And MCU mode)
Video input
2 × MIPI DPHY CSI (Supports MIPI V1.2 version; 1 × 4 Lanes or 2 × 2 Lanes) 1 × MIPI DCPHY CSI RX (DPHY supports V2.0 version with 4Lane/2Lane/1Lane modes; CPHY supports V1.1 version with 0/1/2 Trio modes) 1 × DVP (8/10/12/16-bit, BT.601/BT.656 and BT.1120)
Audio output
1 × HDMI2.1(4096×2160@120Hz)/eDP1.3(4096×2160@60Hz, supports 1Lane/2Lane/4Lane modes) 1 × DP1.4 (4096×2160@120Hz) 1 × EBC Output interface (support E-ink EPD (Electronic Paper Display), 2560×1920) 1 × MIPI_DCPHY_TX (Supports V2.0 version and 0/1/2/3 Lane mode; C-PHY supports V1.1 version and 0/1/2 Trio mode; 2560×1600@60Hz) 1 × LCDC TX (Supports parallel 24-bit RGB mode) 1920×1080@60Hz 16-bit BT1120 mode 1920×1080@60Hz 8-bit BT656 mode 720×576@60Hz And MCU mode)
Audio output
1 × HDMI2.1(4096×2160@120Hz)/eDP1.3(4096×2160@60Hz, supports 1Lane/2Lane/4Lane modes) 1 × DP1.4 (4096×2160@120Hz) 1 × EBC Output interface (support E-ink EPD (Electronic Paper Display), 2560×1920) 1 × MIPI_DCPHY_TX (Supports V2.0 version and 0/1/2/3 Lane mode; C-PHY supports V1.1 version and 0/1/2 Trio mode; 2560×1600@60Hz) 1 × LCDC TX (Supports parallel 24-bit RGB mode) 1920×1080@60Hz 16-bit BT1120 mode 1920×1080@60Hz 8-bit BT656 mode 720×576@60Hz And MCU mode)
Audio
2 × SAI (4T/4R), 3 × SAI (1T/1R), supports I2S/TDM/PCM mode, and supports sampling rates up to 192KHz 2 × SPDIF TX & RX (8ch; Supports up to 24bits resolution) 2 × PDM (Up to 8 channels, audio resolution 16~24 bits, sample rate up to 192KHz, support PDM master receive mode) 2 × DSM (Double-rate interface supported; Supports 8-wire and 16-wire serial transmission modes; DSMC_CLKP/N up to 100MHz)
Os
It supports the RTLinux kernel and has excellent real-time performance, which is widely used in industrial application scenarios. Support Android14, Linux OS, Buildroot, and domestic operating systems, providing a safe and stable system environment for product research and production. It has new industrial features such as a real-time network, Flexbus, hardware resource isolation, and DSMC to meet the needs of different industrial applications.
Dimension
60.00 mm × 42.95 mm × 5.68 mm
Weight
≈15g
Environment
Operating Temperature: -20℃ ~ 60℃ Storage Humidity: 10%~90%RH (non-condensing)
Watchdog
External watchdog support (on-board watchdog IC)
Internet
2 × GMAC (providing RMII or RGMII interfaces to connect external Ethernet PHY); Supports 10/100/1000 Mbps speeds), expandable WiFi, Bluetooth, 4G, 5G through USB, PCIE, SDIO, UART
Interface type
BTB (2 × BTB Socket(80Pin) + 2 × BTB Socket(100Pin))
Usb
1 × USB3.2 Gen1 OTG0 (multiplexed with DP1.4) 1 × USB3.2 Gen1 OTG1 (multiplexed with PCIe 2.1/SATA 3.1)
Can
2 × CAN FD (Supports 8192 bit receive FIFO)
I2c
10 × I2C (Supports 7-bit and 10-bit address modes, data rates up to 100kbps in standard mode and up to 400kbps in fast mode)
Product tutorials
Click Here
Sdk software and firmware files
Click Here
Product tutorialsClick Here
Product datasheetClick Here
SDK software and firmware filesClick Here

Document links will be replaced with the official Firefly resource URLs on request.

Our cooperating carriers: FedEx, DHL, UPS, SF Express

Delivery Area And Cost

Country/Region 0–2kg 2–3kg 3–4kg 4–5kg 5–6kg 6–7kg 7–8kg 8–9kg 9–10kg
Japan, Taiwan, Hong Kong, Macau $15 $20 $25 $30 $35 $40 $45 $50 $55
Singapore, Thailand, Malaysia $20 $25 $30 $35 $40 $45 $50 $55 $60
Indonesia, Philippines $25 $30 $40 $50 $60 $70 $80 $85 $95
South Korea $25 $35 $35 $45 $45 $55 $55 $65 $65
United States, Australia, New Zealand, Canada, UK, and most of Western Europe $30 $45 $55 $65 $75 $85 $95 $105 $115
Other regions (Eastern Europe, Middle East, Latin America, etc.) $50 $65 $80 $95 $110 $125 $135 $150 $165

Shipping time is for reference only; the actual situation shall prevail.

Why Buy From Ai-Paipai?
  • Authorized & Genuine — sourced directly from brand-approved channels.
  • Local Engineering Support — datasheets, SDKs, and pre-flashed images in English and Chinese.
  • OEM / ODM & FPGA Customization — tailor specs, enclosures, and BSP for your project.
  • One-Stop Sourcing — Firefly + youyeetoo + our own FPGA / edge lineup in one store.
View full details

Frequently asked questions

What is iCore-3576Q AIOT System on Module RK3576 used for?
iCore-3576Q AIOT System on Module RK3576 is a SoM / Core Board from Firefly. It is typically used in embedded computing, edge AI inference, industrial control and rapid prototyping, and can be integrated into custom carrier boards or finished devices.

Does iCore-3576Q AIOT System on Module RK3576 include technical support, datasheets or pre-flashed images?
Yes. Ai-Paipai supplies this item as an authorized distributor and provides local engineering support, datasheets, SDKs and pre-flashed system images where applicable, plus OEM / ODM customization for volume projects.

Can I order iCore-3576Q AIOT System on Module RK3576 with OEM / ODM options or CE / FCC / RoHS certification?
OEM / ODM customization (specs, enclosure, BSP) is available, and CE / FCC / RoHS certified options can be provided on request for EU and US imports. Contact us for a quote.

How is iCore-3576Q AIOT System on Module RK3576 shipped, and what is the lead time?
Orders ship worldwide from Shenzhen. Stock items typically dispatch within a few business days; configurable or made-to-order variants take longer. Exact lead time is shown at checkout or on request.

Specifications

Product Datasheet Click Here
Product Wiki Click Here
The Private Deployment of Large Models Large language models such as LLaMa2, ChatGLM, and Qwen. Traditional network architectures, Docker container.
4K@120fps High Frame Rate Video Decoding Supports 4K@120fps decoding (VP9, AVS2, AV1), 4K@60fps decoding (H.264/AVC), 4K@60fps encoding (H.264/AVC), and provides HDMI 2.1 (4K@120fps)/eDP1.3 (4K@60fps), DP1.4 (4K@120fps).
UFS 2.0 with A Data Read Speed of 12Gbps The device supports UFS 2.0 / HS-G3 (12 Gbps), ensuring efficient data storage and access. PCIe NVMe / SATA SSD expansion provides fast data read and write speeds, allowing the device to be easily expanded to TB-level storage capacity.