Reference: https://github.com/JackZeng0208/llama.cpp-android-tutorial

https://github.com/termux/termux-app

termux-change-repo
pkg update

• wget
• git
• docker
• nvidia-driver = 550 (CUDA = 12.4)
• nvidia-container-toolkit https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html
• GPU: RTX3090Tix2 (总显存24GB x 2 = 48GB）
• CPU内存 >= 32GB（需要存放kv cache）

Considering the lack of multi-threaded download support in the official huggingface-cli, and the inadequate error handling in hf_transfer, this command-line tool smartly utilizes wget or aria2 for LFS files and git clone for the rest.

• ⏯️ Resume from breakpoint: You can re-run it or Ctrl+C anytime.
• 🚀 Multi-threaded Download: Utilize multiple threads to speed up the download process.
• 🚫 File Exclusion: Use --exclude or --include to skip or specify files, save time for models with duplicate formats (e.g., .bin and .safetensors).
• 🔐 Auth Support: For gated models that require Huggingface login, use --hf_username and --hf_token to authenticate.
• 🪞 Mirror Site Support: Set up with HF_ENDPOINT environment variable.