To quickly run large language models (LLMs) on your Khadas Edge2 (RK3588S) device, simply run the following script:

khadas_llm.sh

This script will:

• Install necessary dependencies such as cmake
• Prompt you to choose from the following supported models:
  1. DeepSeek 1.5B
  2. DeepSeek 7B
  3. Qwen2 2B-VL
  4. ChatGLM3 6B
• Automatically clone the required repositories
• Download the selected RKLLM model
• Compile the demo
• Configure tokens and context length
• Launch the inference demo optimized for Edge2 NPU

No manual setup required — just run the script and follow the prompts!