PrototypeCommon
matt-k-wong/mlx-flash
Flash weight streaming for MLX: run massive models larger than your RAM on Apple Silicon.
- Owner
- matt-k-wong (personal account)
- Stars
- Stars: 141
- Forks
- Forks: 11
- Language
- Python
- License
- MIT
- Created
- 2026
- Topics
- apple-siliconllm-inferencelm-studiomacosmemory-optimizationmlxllmweight-streamingmachine-learningoptimization
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- apromisedland/Tame_3DStars: 141PythonPrototype
- xianyu110/ecommerce-image-skillsStars: 141PythonPrototype
- actvero/actveroStars: 141PythonPrototype
- pelme/django-compressStars: 141PythonPrototype
- simonw/ratelimitcacheStars: 141PythonPrototype
- lmacken/liveusb-creatorStars: 141PythonPrototype