mlx-flash
Flash weight streaming for MLX: run massive models larger than your RAM on Apple Silicon.
matt-k-wong/mlx-flash
View on GitHub ↗Flash weight streaming for MLX: run massive models larger than your RAM on Apple Silicon.
mlx-flash grew +3.0% in the last 30 days, ranks 225th of 303 in Inference Optimization, last commit 134 days ago.
Star trajectory
115 days tracked2026-07-02138 stars today2026-10-25
Momentum
+3.0% in 30d, above the Inference Optimization median of +1.5%.
Maintenance
Last commit 134 days ago, staler than the median of 15d.
How it compares in Inference Optimization
mlx-flash
138
stars
+3.0% 30d
commit 134 days ago
Inference Optimization median
257
stars
+1.5% 30d
commit ~15d ago
Leader · supertonic
13.8k
stars
-0.2% 30d
commit 45 days ago
Ranked 225th of 303 by stars.
- Language
- Python
- License
- MIT License
- Contributors
- 1
- Forks
- 11
- Watchers
- 1
- Open issues
- 0
- Releases
- 2
- Created
- 2026-03-20
- Stars this week
- +0
You've seen where mlx-flash stands today.
Get the moves before everyone else: the 5 Inference Optimization repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.