Edge AI Tech Blog
Running Local LLMs on RK3588: Real Benchmarks a...
Real RK3588 local-LLM benchmarks: 8-11 tok/s at 1.5B, 5-7 at 3B, 3-4 at 8B on the NPU, roughly 2x faster than the same board CPU. Includes sources, test conditions and...
Running Local LLMs on RK3588: Real Benchmarks a...
Real RK3588 local-LLM benchmarks: 8-11 tok/s at 1.5B, 5-7 at 3B, 3-4 at 8B on the NPU, roughly 2x faster than the same board CPU. Includes sources, test conditions and...
Edge AI Single Board Computer Selection Guide f...
A workload-first framework for choosing an edge AI SBC: match your task, interfaces and power budget to the right class of board before comparing specs.
Edge AI Single Board Computer Selection Guide f...
A workload-first framework for choosing an edge AI SBC: match your task, interfaces and power budget to the right class of board before comparing specs.
FPGA vs GPU for AI Inference: Latency, Power an...
When does an FPGA beat a GPU for AI inference? A practical breakdown of deterministic latency, power efficiency, precision flexibility and development cost.
FPGA vs GPU for AI Inference: Latency, Power an...
When does an FPGA beat a GPU for AI inference? A practical breakdown of deterministic latency, power efficiency, precision flexibility and development cost.
Ai-Paipai Launches Development Program for the ...
PRODUCT · EDGE AI Ai-Paipai Launches Development Program for the NVIDIA Jetson Orin Nano 2 Ai-Paipai Engineering Team · September 2026 · 6 min read NVIDIA has unveiled the Jetson Orin Nano 2,...
Ai-Paipai Launches Development Program for the ...
PRODUCT · EDGE AI Ai-Paipai Launches Development Program for the NVIDIA Jetson Orin Nano 2 Ai-Paipai Engineering Team · September 2026 · 6 min read NVIDIA has unveiled the Jetson Orin Nano 2,...
RK3588 vs NVIDIA Jetson Orin Nano: Which Edge A...
Choosing an edge AI platform in 2026 is harder than ever: ARM-based AI SoCs have closed the gap with NVIDIA's GPU modules on price, while NVIDIA keeps widening the software...
RK3588 vs NVIDIA Jetson Orin Nano: Which Edge A...
Choosing an edge AI platform in 2026 is harder than ever: ARM-based AI SoCs have closed the gap with NVIDIA's GPU modules on price, while NVIDIA keeps widening the software...