# Parameter Efficient Fine-Tuning

> Source: https://sukruyusufkaya.com/en/glossary/parameter-efficient-fine-tuning
> Updated: 2026-05-13T20:01:09.342Z
> Type: glossary
> Category: uretken-yapay-zeka-ve-llm
**TLDR:** A fine-tuning approach that adapts a model using a limited number of parameters instead of updating the full model.

<p>PEFT greatly reduces cost by removing the need to fully retrain large models for every task. Since task adaptation can be achieved with only a small number of added or trainable parameters, storage, training, and deployment efficiency all improve. It is especially valuable in enterprise multi-task scenarios.</p>