What it does
This skill applies Half-Quadratic Quantization (HQQ) to large language models, reducing them to 4-, 3- or 2-bit precision. It works without calibration datasets.
It suits cases where a model needs fast quantization without preparing calibration data, or where the quantized model will be deployed with vLLM or HuggingFace Transformers. The publisher's description does not cover the steps needed to run it.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 18 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 26
optimization-hqq
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.
v1.0.0As shown on www.aitmpl.com when we last read it