Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub
安装
npx skills add huggingface/skills --skill hf-memnpx skills add huggingface/skills --skill hf-mem -a claude-code -gnpx skills add huggingface/skills --skill hf-mem -a codex -ggemini skills install https://github.com/huggingface/skills.git --path skills/hf-memgh skill install huggingface/skills hf-memgit clone --depth 1 https://github.com/huggingface/skills /tmp/huggingface__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/huggingface__skills/skills/hf-mem ~/.claude/skills/hf-mem # Claude Code
cp -R /tmp/huggingface__skills/skills/hf-mem ~/.agents/skills/hf-mem # Codex, Cursor, Gemini CLI, Copilot, OpenCode