Jun Kim Joins Hugging Face to Advance oMLX and the Apple Silicon Ecosystem

Jun Kim Joins Hugging Face to Advance oMLX and the Apple Silicon Ecosystem Jun Kim, the creator and maintainer of oMLX, has joined Hugging Face to work full-time on the project and support the broader MLX local AI ecosystem on Apple Silicon. oMLX transitions from a side project into a fully funded, maintained initiative led by Jun Kim under the Apache 2.0 license. The project will serve as a testbed for new features while upstreaming improvements to dependencies like mlx-lm and mlx-vlm. A key objective is streamlining the transition from Hugging Face transformers definitions to reference MLX implementations. Impact on oMLX Development and Governance Joining Hugging Face shifts oMLX from a side endeavor to a fully funded, permanently maintained project designed for faster development and long-term stability. Jun Kim will continue leading the project and guiding contributors, and oMLX will retain its Apache 2.0 open-source license. Ecosystem Goals and Transformers Integration Hugging Face aims to unblock local AI execution on Apple Silicon by collaborating closely with tools like mlx-lm, mlx-vlm, and LMStudio. A primary technical priority is accelerating the conversion of transformers model definitions into reference MLX implementations that can be utilized across multiple inference engines.

oMLX 创作者 Jun Kim 加入 Hugging Face，加速支持苹果 MLX 社区 oMLX 的创建者兼维护者 Jun Kim 正式加入 Hugging Face，双方将合力推进苹果 MLX 生态建设，赋能本地 AI 的运行与开发。 Jun Kim 加入后，oMLX 从兼职副业转变为获得资金与全职支持的长期维护项目，继续保持 Apache 2.0 开源协议并由其主导。 oMLX 将作为新想法的试验田，依托 mlx-lm 和 mlx-vlm 等底层成果并向上游反哺，深化与相关项目团队的合作。 重点推进从 Transformers 模型定义到 MLX 参考实现的快速过渡，简化新模型在 MLX 上的运行流程。 oMLX 项目获得全职维护支持 随着 Jun Kim 加入 Hugging Face，oMLX 正式从个人业余项目升级为获得全额资助与全面维护的长期项目。这一转变旨在提升开发速度与稳定性，帮助其更好地引导社区贡献者。项目未来将继续保持 Apache 2.0 开源协议，并由 Jun Kim 继续牵头推进。 深化生态合作与模型支持流程 Hugging Face 致力于降低开发者在本地运行 AI 的门槛。oMLX 将依托 mlx-lm 与 mlx-vlm 等项目作为测试基础，并在适当时机向上游回馈代码，加强与 LMStudio 等生态伙伴的合作。具体工作重心之一是打通 Transformers 模型定义向 MLX 参考实现的快速转换链路，以便各类推理引擎能够更快运行新模型并发挥各自特性。

We are super excited to welcome Jun as our newest team member 🔥. We are completely invested in local AI, and MLX is a central piece of the ecosystem. We are delighted that Jun chose us to set up home and continue contributing to MLX. MLX is Apple's framework for local AI, especially optimized for Apple Silicon. We are big MLX supporters since it was the Christmas present from Awni and Angelos in 2023, and proud that Hugging Face is the Hub where people find MLX models and contribute their own. Usage of open, local AI is accelerating, and we believe in a healthy ecosystem where people can find the tools that work for them. What is the impact for oMLX? Stability, and hopefully faster development! Graduating from a side job to a fully maintained and funded project will allow Jun to better guide the contributors and build for the long-term. oMLX stays Apache 2.0, and Jun keeps leading it as before. What is the impact for MLX at large? Our end goal is to unblock the community to run local AI in any shape or form, and provide the tools and building blocks to make that happen. We expect oMLX to serve as a testbed for new ideas, while leveraging the foundational work of the dependencies it already relies upon, such as mlx-lm or mlx-vlm . We believe that strong modeling and inference libraries help the community, so we'd love to upstream work to wherever it makes sense. We have been collaborating with many projects mlx-lm, mlx-vlm, LMStudio, and we hope we can strengthen the relationship 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 one can focus on the unique features they provide. The transformers library has become the reference for ML model definitions, we want to streamline the process to make new transformers models run on MLX. We are incredibly excited about the future. Welcome, Jun! 🙌