{"id":"mlx","name":"MLX","maker":"Apple","url":"https://mlx-framework.org","repo":"ml-explore/mlx","package":"pypi:mlx","summary":"An array framework from Apple machine learning research for Apple silicon, with Python, Swift, C++ and C APIs.","details":"MLX uses unified memory and lazy computation and is the base of tools that run models locally on Macs. It is a library, not a model server, and MLX LM and similar packages are built on it.","open_source":true,"hosted":false,"verified":"2026-11-15","category":"runtimes","category_name":"Local and self-hosted model runtimes","page":"https://modelmoot.com/tools/mlx","reviewed":"2026-11-15","checked":{"at":"2026-11-15T15:07:43.409Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}