Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community
- ID
- 27123
- Status
- summarized
- Published
- 22 Sep 2026, 8:00 AM
- Fetched
- 22 Sep 2026, 3:05 PM
- Provider
- Hugging Face Blog
- Category
- developer-ai
- Original URL
- https://huggingface.co/blog/omlx
- Source URL
- https://huggingface.co/blog/feed.xml
Summary
- Score
- 5.5
- Created
- 22 Sep 2026, 3:06 PM
- Tags
- Audience
- developersai_ml_learnersai_agent_users
What happened
Jun Kim, creator and maintainer of oMLX (an MLX-based library for local AI on Apple Silicon), has joined Hugging Face to work on MLX full-time. oMLX remains Apache 2.0 and Jun continues leading it, but the project moves from a side project to a funded effort. A key focus will be streamlining the conversion path from transformers model definitions to reference MLX implementations that different inference engines can consume.
Why it matters
If you ship local AI on Apple Silicon, the transformers-to-MLX conversion pipeline is a real bottleneck when new models drop — this hire signals that bottleneck may ease, making it faster to run newly released models on Mac. No action needed today, but worth tracking oMLX and mlx-lm releases if you depend on MLX for local inference or agent workflows.
Discussion angle
What's the current state of running open models locally on Apple Silicon in Malaysia — is MLX practical enough for production agents, or are people still defaulting to cloud APIs given bandwidth and cost trade-offs?