Hugging Face announced that Jun Kim, creator and maintainer of oMLX, is joining the team to support the MLX ecosystem. The post frames MLX, Apple’s framework for local AI optimized for Apple Silicon, as a central piece of Hugging Face‘s investment in local AI. Hugging Face notes it has supported MLX since it was released by Awni and Angelos in 2023, and that its Hub is where people find and contribute MLX models.

The direct impact for oMLX is stability and faster development. Moving from a side project to a fully maintained and funded project will let Jun guide contributors and build long-term. oMLX remains Apache 2.0 and Jun keeps leading it. For the broader MLX ecosystem, Hugging Face‘s goal is to unblock the community to run local AI in any form and provide the tools and building blocks to do so. The expectation is that oMLX will act as a testbed for new ideas while building on its existing dependencies such as mlx-lm and mlx-vlm.

Hugging Face explicitly wants to upstream work to strong modeling and inference libraries where it makes sense. The company has already collaborated with projects including mlx-lm, mlx-vlm, and LMStudio, and hopes to strengthen relationships with Cheng, Prince, Yagil, and their teams. A concrete focus area is smoothing the transition from a transformers model definition to a reference MLX implementation that different engines can consume, allowing each engine to focus on its unique features. Since the transformers library has become the reference for ML model definitions, streamlining that process would help new transformers models run on MLX more quickly.

The overall message is excitement about the future of open, local AI and the role MLX and oMLX will play in it.