home/categories/computational-chemistry/nousresearch-hermes-agent-skills-mlops-inference-gguf-skill-md
computational-chemistryresearch
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
maintainer
NousResearch
更新於 3/9/2026
星標
54282
分支
7115
quick start
Installation and usage
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
安裝
$ install --globalskills.sh
使用
安裝後，您可以透過在終端機執行以下指令來使用此技能：
skills use gguf-quantization