# What is PEFT? Definition & Technical Mechanics

> **Source:** [SPIDITS AI AI Glossary](https://spidits.com/ai-glossary)  
> **Category:** Model Training  
> **Canonical Citation:** [https://spidits.com/ai-glossary/peft](https://spidits.com/ai-glossary/peft)

## Definition
Parameter-Efficient Fine-Tuning (PEFT) is a collection of training methods designed to fine-tune large foundation models by adapting only a tiny subset of additional parameters, while freezing the base model's weights.

## Architectural Mechanics & Deep Dive
PEFT (Parameter-Efficient Fine-Tuning) is a collection of techniques (including LoRA, Prefix Tuning, and Prompt Tuning) designed to adapt large pre-trained models to specific tasks while keeping the majority of original model parameters frozen. PEFT reduces the computational and storage overhead of fine-tuning, requiring only a fraction of GPU memory.

## Industry Applications & Real-World Use Cases
Low-compute model adaptations, adapter model hosting, and custom domain specialization

## Frequently Asked Questions

### What are typical PEFT methods?
LoRA (Low-Rank Adaptation), Prefix Tuning, and Prompt Tuning are common PEFT approaches.

### Why is PEFT critical for enterprise AI?
It slashes compute/storage costs by 95%+, enabling businesses to store lightweight task-specific adapters rather than separate multi-gigabyte models.

## Related Terminology
- [lora](https://spidits.com/ai-glossary/lora)
- [fine-tuning](https://spidits.com/ai-glossary/fine-tuning)
- [llm](https://spidits.com/ai-glossary/llm)

---
*From the SPIDITS AI Knowledge Base (336+ terms indexed). Explore full technical definitions: [https://spidits.com/ai-glossary](https://spidits.com/ai-glossary)*