Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.
Install
npx skills add huggingface/skills --skill huggingface-local-modelsnpx skills add huggingface/skills --skill huggingface-local-models -a claude-code -gnpx skills add huggingface/skills --skill huggingface-local-models -a codex -ggemini skills install https://github.com/huggingface/skills.git --path skills/huggingface-local-modelsgh skill install huggingface/skills huggingface-local-modelsgit clone --depth 1 https://github.com/huggingface/skills /tmp/huggingface__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/huggingface__skills/skills/huggingface-local-models ~/.claude/skills/huggingface-local-models # Claude Code
cp -R /tmp/huggingface__skills/skills/huggingface-local-models ~/.agents/skills/huggingface-local-models # Codex, Cursor, Gemini CLI, Copilot, OpenCode