Automated read-only mirror of HyperFrames for Lynlo template discovery and Pack research
skill
hqq-quantization
ANo problem foundqcmuu/AI-Research-Skills
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.
hqq-quantization got grade A on our automated scan on 2026-10-21.
Before you install
- Read any scripts this skill ships.
- Note every URL it fetches.
- Check allowed-tools and hooks.
Embed this grade
Add this badge to your README. It shows the current grade from CheckSkills.
Report this skill if the grade looks wrong, or if something slipped through.
Related
My dotfiles (.zshrc, .gitconfig, terminal config, ghostty, starship, etc.) managed with Chezmoi
Deterministic supervisor for dispatching agent work across local, Docker, and Sprite runners.
My personal website
Design a PostgreSQL schema for a new domain entity.