Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community

Hugging Face announced that Jun Kim, creator and maintainer of oMLX, is joining as its newest team member, saying it is fully invested in local AI and that MLX is a central piece of that ecosystem. MLX is Apple's framework for local AI, especially optimized for Apple Silicon. Hugging Face says it has been a major MLX supporter since MLX arrived as a Christmas present from Awni and Angelos in 2023, and it is proud that Hugging Face Hub is where people find MLX models and contribute their own. The company adds that usage of open, local AI is accelerating and that it believes in a healthy ecosystem where people can find the tools that work for them.

For oMLX, the impact is stability and hopefully faster development. Graduating from a side job to a fully maintained and funded project will allow Jun to better guide contributors and build for the long term. oMLX stays Apache 2.0, and Jun keeps leading it as before.

For MLX at large, Hugging Face says its end goal is to unblock the community to run local AI in any shape or form and to provide the tools and building blocks to make that happen. It expects oMLX to serve as a testbed for new ideas while leveraging the foundational work of dependencies it already relies on, such as mlx-lm and mlx-vlm. Hugging Face believes strong modeling and inference libraries help the community, so it would love to upstream work wherever it makes sense. It has been collaborating with many projects including mlx-lm, mlx-vlm, and LMStudio, and hopes to strengthen relationships with Cheng, Prince, Yagil, and their teams to better serve the community together.

Concretely, one focus area is the quick transition from a transformers model definition to a reference MLX implementation that can be consumed by different engines, so each engine can focus on the unique features it provides. The transformers library has become the reference for ML model definitions, and Hugging Face wants to streamline the process so new transformers models can run on MLX. It says it is incredibly excited about the future and welcomes Jun.