PEFT
๐ค PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Our verdict
A usable project with some maintenance caveats. This assessment is derived from GitHub's own repository metrics on 2026-08-30, not from hands-on testing.
๐ค PEFT: State-of-the-art Parameter-Efficient Fine-Tuning. The project is written primarily in Python, released under Apache-2.0, and has 21,607 stars and 2,457 forks on GitHub. 348 contributors have committed to it, and the most recent push was 2026-08-28. The latest tagged release is v0.20.0 (2026-07-28). Figures come from the GitHub API on 2026-08-30 and are refreshed daily; the score below weighs adoption, maintenance, release discipline, contributor breadth, licence clarity and issue hygiene.
Repository
- Licence
- Apache-2.0
- Language
- Python
- Last push
- 2026-08-28
Releases
-
v0.20.0v0.20.0 -
v0.19.1v0.19.1 -
v0.19.0v0.19.0 -
v0.18.10.18.1 -
v0.18.00.18.0: RoAd, ALoRA, Arrow, WaveFT, DeLoRA, OSF, and more -
v0.17.10.17.1
Pros and cons
Pros
Pricing
- Free tierYes
- LicenceApache-2.0
- Self-hostYes, source is public
- Public price listNot published
PEFT does not publish a web price list. For consumer apps that usually means pricing appears inside the product; for enterprise tools it means talking to sales. Why we do this
Visit huggingface.coTrends
Price points are recorded when a price moves, not on a schedule, so a flat run means the price held. Release cadence comes from GitHub releases. A series appears only once we have watched it for long enough to have more than one observation.
User reviews
No one has reviewed PEFT here yet. Reviews are moderated before they appear, and our own score is editorial and separate from user ratings, though once reviews land they do lift it.
Used PEFT? Review it.
Sign in to rate it. One account, one review per tool, so the score means something.
Requiring an account is how we keep this page free of drive-by spam. We never sell your address.
PEFT alternatives
PyTorch Image Models (timm)
The largest collection of PyTorch image encoders / backbones.…
fastai
The fastai deep learning library
LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL…
DeepSpeed
DeepSpeed is a deep learning optimization library that makes…
Hugging Face Datasets
๐ค The largest hub of ready-to-use datasets for AI…
Label Studio
Label Studio is a multi-type data labeling and annotation…
Side by side
| Tool | Our score | From | Free tier | Best for | |
|---|---|---|---|---|---|
| PEFT this page | 7.7 | - | Yes | ||
| PyTorch Image Models (timm) | 7.7 | - | Yes | ||
| fastai | 7.4 | - | Yes | ||
| LlamaFactory | 7.3 | - | Yes | ||
| DeepSpeed | 7 | - | Yes | ||
| Hugging Face Datasets | 7 | - | Yes | ||
| Label Studio | 6.7 | - | Yes |
Questions
Is peft free?
Yes. peft advertises a free tier on its own site.
How much does peft cost?
peft does not publish a web price list. For consumer apps that usually means pricing appears inside the product; for enterprise tools it means talking to sales.
Is peft open source?
Yes. peft is a public repository released under Apache-2.0. You can self-host or inspect the source directly.
How is peft scored here?
peft scores 7.7 out of 10. That comes from a desk review of public evidence, which is capped at 8.5 out of 10: public pricing, documentation, maintenance signals and how much we could actually verify. Affiliate relationships are excluded from scoring entirely. The full rubric is published on our methodology page.