---
title: "AWQ, GPTQ & SmoothQuant"
description: "Why four-bit weights lose values, and how three methods respond: GPTQ's error compensation, the channels AWQ protects, SmoothQuant's migration."
canonical_url: "https://fanout.sh/inference-eng/curriculum/11-03"
md_url: "https://fanout.sh/inference-eng/curriculum/11-03.md"
access: "pro-preview"
---

# AWQ, GPTQ & SmoothQuant

Why four-bit weights lose values, and how three methods respond: GPTQ's error compensation, the channels AWQ protects, SmoothQuant's migration.

- Access: Fanout Pro (public preview)

## Public preview

A number format is a container. It fixes how many bits a value gets and how those bits are read, and it decides nothing about which value goes in. Store a matrix at four bits per entry when it was written at sixteen, and most of its values no longer have a slot of their own. Move every one to…

## In this lesson

- Activation outliers
- GPTQ's compensation step
- The channels AWQ protects
- Migrating the difficulty
- The three methods compared

## Continue learning

Pro unlocks the complete lesson, video, practice, and code where available.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md