Fact · Speech recognition
MLX is an array framework for machine learning on Apple silicon, from Apple's machine learning research team.
Checked against its source on October 17, 2026
In the source's own words
“MLX is an array framework for machine learning on Apple silicon, brought to you by Apple machine learning research.”
MLX: README (ml-explore/mlx, GitHub), Apple machine learning research, GitHub (ml-explore/mlx), 2026, Introduction.
Open the original- What it measures
- The MLX port of Whisper is built on this framework and runs on Apple silicon Macs.
- What it does not show
- This describes the framework. It does not measure the speed of any Whisper model under MLX.