home/categories/llm-ai/davila7-claude-code-templates-cli-tool-components-skills-ai-research-optimization-bitsandbytes-skill-md
llm-aidata-ai
quantizing-models-bitsandbytes
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
maintainer
davila7
Atualizado 1/20/2026
Estrelas
17577
Forks
1576
quick start
Installation and usage
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
Instalação
$ install --globalskills.sh
Uso
Depois de instalar, você pode usar esta skill executando o seguinte comando no terminal:
skills use quantizing-models-bitsandbytes