
Hqq Quantization
- 11.4k repo stars
- Updated June 16, 2026
- Orchestra-Research/AI-Research-SKILLs
For integrating Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets,
About
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.. This is a developer tool for building and integrating AI-powered features.
- AI
- Developer tool
Hqq Quantization by the numbers
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/Orchestra-Research/AI-Research-SKILLs --skill 10-optimization/hqq/SKILL.mdAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| repo stars | ★ 11.4k |
|---|---|
| Last updated | June 16, 2026 |
| Repository | Orchestra-Research/AI-Research-SKILLs ↗ |
What it does
For integrating Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets,