Menu

Individual skill

awq-quantization

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

plugins/KalarisLabs/research-agent-skills/skills/awq-quantization/SKILL.md

Read pinned source

Source commit d780783eba4ecc7c8b9429f95c9362df95f07c61

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 4, 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)
1,532
Repository last updated
Nov 6, 2026
License
Apache-2.0

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

Declared tags are partial or unavailable.

Files and excerpt

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

Browse files
Read excerpt

# AWQ (Activation-aware Weight Quantization)

4-bit quantization that preserves salient weights based on activation patterns, achieving 3x speedup with minimal accuracy loss.

## When to use AWQ

**Use AWQ when:**
- Need 4-bit quantization with <5% accuracy loss
- Deploying instruction-tuned or chat models (AWQ generalizes better)
- Want ~2.5-3x inference speedup over FP16
- Using vLLM for production serving
- Have Ampere+ GPUs (A100, H100, RTX 40xx) for Marlin kernel support

**Use GPTQ instead when:**