---
title: "LoRA & QLoRA"
description: "Why training a second full-size weight matrix is costly, how LoRA trains two small matrices beside a frozen layer, its first update, and what QLoRA adds."
canonical_url: "https://fanout.sh/ai/lessons/fine-tuning-lora"
md_url: "https://fanout.sh/ai/lessons/fine-tuning-lora.md"
access: "pro-preview"
---

# LoRA & QLoRA

Why training a second full-size weight matrix is costly, how LoRA trains two small matrices beside a frozen layer, its first update, and what QLoRA adds.

- Access: Fanout Pro (public preview)
- Module: How to Fine-Tune Models

## A glimpse of LoRA & QLoRA

A model layer can contain a large matrix of learned weights. Adapting the layer by training a second equally large matrix would require another large set of gradients and optimizer state.

LoRA, short for low-rank adaptation, trains a change built from two smaller matrices. The original weight matrix stays frozen.

## Continue learning

Pro unlocks guided learning, complete notes, practical walkthroughs, exercises, and every AI Research lesson.

---
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