RK1828 AI Accelerator M.2 Module

Install and verify RK1828 on RK3576 by inserting the M.2 card, powering with 12V, installing RKNN3 drivers, then using rknn-smi to confirm device health, versions, and PCIe connection; finally run rknn3_session_test with Qwen3-0.6B RKNN model files to validate LLM inference, like a quick boot checklist for NPU deployment.

How to deploy and chat with offline LLMs on a DFRobot RK3576 board: install RK182x drivers on Debian 12, verify the RK1828 NPU via rknn-smi info, then download pre-converted RKNN models and the offline-model app, place model files with consistent prefixes under /userdata/models, and copy rkllm3_server.sh, run.sh, and switch_to.sh into each model folder. It’s like setting up a local AI kiosk: you prepare the hardware, load models such as Qwen2.5-3B or MiniCPM-V-4, and use switch_to.sh to select the active model. Finally, run start.sh to install or start Docker, then open <board-ip>:5000 in a browser to access the web chat UI, monitor logs with docker logs, and manage the container using standard Docker commands.