Skip to content
ai

QLoRA

Quantized Low-Rank Adaptation

Definition

QLoRA combines 4-bit quantization of the base model with LoRA fine-tuning, enabling fine-tuning of very large models (65B+ parameters) on a single consumer GPU. The base model is loaded in NF4 (normalized float 4-bit) format and kept frozen, while LoRA adapters are trained in 16-bit precision.

QLoRA demonstrated that high-quality fine-tuning of 65B models is feasible on a single 48GB GPU.

Related Terms

LoRA
Low-Rank Adaptation
Quantization
Model Quantization
PEFT
Parameter-Efficient Fine-Tuning
Fine-tuning
Model Fine-tuning
INT4
4-bit Integer Quantization
← Back to Glossary

Ship secure code faster

Crash Override integrates security into the developer workflow. No context switching, no waiting on reviews.

Talk to a Human See the Product