Hugging Face Transformers Adds Native MLX Support for Apple Silicon

Summary

Hugging Face has published a blog post authored by Pedro Cuenca and Awni Hannun detailing the integration of Apple's MLX framework directly into the Hugging Face Transformers library. The title — "The PR you would have opened yourself" — suggests this was a highly requested community contribution that bridges the gap between the dominant Transformers ecosystem and Apple's MLX, an array framework optimized for machine learning on Apple Silicon hardware. This integration allows developers to run