home/categories/machine-learning/davila7-claude-code-templates-cli-tool-components-skills-ai-research-optimization-hqq-skill-md
machine-learningdata-ai

hqq-quantization

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

davila7
maintainer
davila7
Updated 1/20/2026
Stars
17577
Forks
1576
quick start

Installation and usage

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

Installation
$ install --globalskills.sh
Usage

Once installed, you can use this skill by running the following command in your terminal:

skills use hqq-quantization