Load and run almost any open AI model from one Python library
Made by Hugging Face
View profile on GitHub (opens in a new tab)The Python library that defines how open models are written down, covering text, images, audio, video and combinations of them, for both running a model and training one.
Its real role is as the common reference: if a model’s definition lands here, the rest of the ecosystem — training frameworks, serving engines, and neighbouring libraries like llama.cpp and MLX — can work from that same definition instead of each reimplementing it. More than a million model checkpoints on the Hugging Face Hub are usable through it, which is what makes trying a new model a matter of changing a name.
Can I use this?
You'll need Python 3.10 or later and PyTorch · Setup needed
Worth knowing It is a library, not an application: it gives you the model, not a chat window or a server, and running a large model still needs the hardware that model needs. It is a very large dependency with a fast release cadence, and code written against one version does not always run unchanged against a later one. Each model you load carries its own licence, which the library does not enforce for you. Apache 2.0. BuildTube has not run or verified this software.
Why it's here
Not trending this week
Last seen on the GitHub trending list on 20 September 2026. It stays on BuildTube so you can still find it.
- 166,999 people have starred it on GitHub.
Numbers checked on 6 October 2026; not refreshed since.
Behind it
See the code on GitHubBuildTube has not run or verified this project. Everything above is written from what the creator published.
Made this?