MLX is Apple's framework for local AI, optimized for Apple Silicon. Hugging Face has supported MLX since its launch as a Christmas present from Awni Hannun and Angelos Katharopoulos in 2023, and the Hub now serves as the primary repository where people find and contribute MLX models.

The project is graduating from a side effort to a fully maintained and funded initiative

The project is graduating from a side effort to a fully maintained and funded initiative, which will provide stability and faster development. Jun will lead the effort full-time, better guiding contributors and planning for the long term. oMLX remains Apache 2.0 licensed with Jun continuing as lead.

The goal is to unblock the community to run local AI in any form and provide the necessary tools and building blocks. oMLX will serve as a testbed for new ideas while leveraging foundational dependencies like mlx-lm and mlx-vlm. Hugging Face plans to upstream work wherever it makes sense and has been collaborating with projects including LMStudio, working to strengthen relationships with teams led by Cheng, Prince, and Yagil to better serve the community.

A concrete focus area is streamlining the transition from a transformers model definition to a reference MLX implementation that different engines can consume, allowing each to focus on unique features. The transformers library has become the reference for ML model definitions, and the goal is to make this process smoother so new transformers models can run on MLX more readily.

Welcome, Jun! 🙌