File 002 · Local Intelligence
Record 016 · Runtimes · 2023
23.16.UMLX
Apple
“Apple's array framework that made local LLMs and diffusion native on M-series.”
NumPy for the unified memory Mac.
MLX (and mlx-lm) uses unified memory so a 128GB Mac Studio is a model host, not a GPU-rental client. The local-Mac stack.
Opened first-class local ML on Apple silicon.
Filed notes
- Unified-memory arrays
- mlx-lm inference
- Fine-tune on Mac
SIC
7372
Prepackaged Software
NAICS
511210
Software Publishers
