QLoRA: Efficient Finetuning of Quantized LLMs

On the reading lists

• #136 in the Top 500 (2026 edition)
• #20 in Deep learning (2026 edition)

Why it matters

Combined 4-bit quantization with LoRA, democratizing fine-tuning of very large models.

Condensed from the expert lists' notes.

The record

First released

2023 (from arXiv 2305.14314)

Citations

6,016 citations, as counted by Papers With Code (CC BY-SA 4.0)

Named by

both expert lists

Also relevant to

Language, speech & LLMs

Score

0.615 · computed rank 136 · consensus 0.79, must-read 0.5, citations percentile 0.938 (2020s · deep-learning), awards 0, existing lists 0. Method