Individual skill

quantization

Quantize models for efficient inference — precision formats, calibration, accuracy validation, and hardware considerations. Use when models are too big, slow, or expensive to serve at full precision.

skills/quantization/SKILL.md

Read pinned source

Source commit faf37c0859ebf627bfcb5225e8057d088691e0ae

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: Yes
Observed behavior: Not checked yet
Last checked: Nov 8, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 54
Repository last updated: Oct 10, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-skills Repository topic
ai-agents Repository topic
ai-agents-automation Repository topic
ai-skills Repository topic
awesome Repository topic
awesome-list Repository topic
chatgpt Repository topic
claude-skills Repository topic
meta-ai Repository topic
muse-ai Repository topic
engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 4,033 bytes

Read excerpt


# Model Quantization

Quantization shrinks models by representing weights (and activations) in fewer bits — 16-bit to 
8-bit to 4-bit — cutting memory, speeding inference, and lowering cost. Modern methods preserve 
quality remarkably well, but the details matter.

## Overview

The trade: fewer bits per weight means smaller, faster models with some precision loss. 
Post-training quantization (PTQ) converts an existing model without retraining — fast and usually 
sufficient. Quantization-aware training (QAT) trains with quantization simulated — better 
quality, more effort. Weight-only quantization shrinks memory (the common bottleneck); 
weight+activation quantization also speeds compute. Calibration data tunes the quantization ranges 
— use representative data.