PyTorch Image Models (timm)
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights - ResNet, ResNeXT, Effic
Add this badge to your site
Run or build PyTorch Image Models (timm)? Paste this where your reviews or press logos go. It links to this review and always shows the current score and review date. Every tool we score 7.0 or higher can use it. It is free, and it does not change a score.
Need a launch video for PyTorch Image Models (timm)? We make 45 to 90 second explainers from $79. See the explainer service
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.
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights - ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more. The project is written primarily in Python, released under Apache-2.0, and has 37,265 stars and 5,225 forks on GitHub. 201 contributors have committed to it, and the most recent push was 2026-11-03. The latest tagged release is v1.0.31 (2026-11-03). Figures come from the GitHub API on 2026-11-07 and are refreshed weekly; the score below weighs adoption, maintenance, release discipline, contributor breadth, licence clarity and issue hygiene.
Reviewed by AI Review Rating from GitHub API data How we score
Repository
- Licence
- Apache-2.0
- Language
- Python
- Last push
- 2026-11-03
Releases
-
v1.0.31Release v1.0.31 -
v1.0.30Release v1.0.30 -
v1.0.29Release v1.0.29 -
v1.0.28Release v1.0.28 -
v1.0.27Release v1.0.27 -
v1.0.26Release v1.0.26
Pros and cons
Pros
Pricing
- Free tierYes
- LicenceApache-2.0
- Self-hostYes, source is public
- Public price listNot published
PyTorch Image Models (timm) 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.
Changelog
User reviews
No one has reviewed PyTorch Image Models (timm) 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 PyTorch Image Models (timm)? 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.
PyTorch Image Models (timm) alternatives
PEFT
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
🥈 
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
🤗 The largest hub of ready-to-use datasets for AI…
ComfyUI
The most powerful and modular diffusion model GUI, api…
Side by side
| Tool | Our score | From | Free tier | Best for | |
|---|---|---|---|---|---|
| PyTorch Image Models (timm) this page | 7.7 | - | Yes | ||
| 🥇PEFT | 7.7 | - | Yes | ||
| 🥈fastai | 7.4 | - | Yes | ||
| 🥉LlamaFactory | 7.3 | Free | Yes | ||
| DeepSpeed | 7 | - | Yes | ||
| Hugging Face Datasets | 7 | - | Yes | ||
| ComfyUI | 6.9 | - | Yes |
Questions
Is pytorch-image-models free?
Yes. pytorch-image-models advertises a free tier on its own site.
How much does pytorch-image-models cost?
pytorch-image-models 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 pytorch-image-models open source?
Yes. pytorch-image-models is a public repository released under Apache-2.0. You can self-host or inspect the source directly.
How is pytorch-image-models scored here?
pytorch-image-models 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.