Python · MIT
matt-k-wong/mlx-flash
Flash weight streaming for MLX: run massive models larger than your RAM on Apple Silicon.
★ 141
Stars
11 forks · 0 open issues
+2.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
24.1
Momentum / 100
see the breakdown below
7mo ago
Created
last push 4mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 2.1 | +2.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 12.9 | last week ran 1.86× the monthly pace |
| Freshness | 15 | 2.9 | last push 4mo ago; decays to zero at 180 days |
| Scale | 15 | 6.2 | 141 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 24.1 | sum of the above |
Detail
| Topics | apple-siliconlarge-language-modelsllmllm-inferencelm-studiomachine-learningmacosmemory-optimizationmetalmlxoptimizationweight-streaming |
| Matched on | LLM & Inference (large-language-models, llm-inference) |
| Short window | +2 stars over 7 days = 0.3/day |
| Long window | +4 stars over 26 days = 0.2/day |
| Lifetime average | 0.61 stars/day over 230 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |