Özer Cem KELAHMETKELAHMET
Glossary · Generative AI and LLMs

What is QLoRA? Definition and meaning

Combines 4-bit quantization of the frozen base with LoRA adapters, which cuts memory enough to fine-tune large models on one GPU.

Definition

QLoRA: Combines 4-bit quantization of the frozen base with LoRA adapters, which cuts memory enough to fine-tune large models on one GPU.

In short: LoRA on top of a 4-bit quantized base model.

When it is used

Fine-tuning large models on limited hardware.

Where it fits

QLoRA belongs to Fine-tuning in the Generative AI and LLMs topic. These are the other terms in the same group:

  • Fine-tuning: Further training of a pretrained model on new data so it performs a specific task, domain or style better.
  • Full fine-tuning: Continues training with all model parameters trainable, rather than a small add-on.
  • SFT: Trains a model on curated prompts and ideal responses so it follows instructions in the desired style.
  • LoRA: Freezes the model and learns small low-rank update matrices for selected layers, so only a small fraction of parameters change.
  • PEFT: A library that implements LoRA, prefix tuning, prompt tuning and related methods on top of Hugging Face models.
  • DPO: Optimizes a model directly on preferred versus rejected answers, without training a separate reward model or running reinforcement learning.
  • RLHF: Trains a reward model from human preference comparisons and then optimizes the language model against it with reinforcement learning.

Learn more

The full guide to QLoRA explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.

Previous term: Qdrant · Next term: Query rewriting

Last updated Nov 18, 2026
Type to search.
    ↑↓ navigate↵ open