arizqi/cpubrrr
Frontier-class LLM inference on a laptop CPU — gpt-oss:20b at ~110 tok/s on Apple M4 Max, 7.5x llama.cpp, no GPU. From-scratch NEON/SME kernels in Rust.
56
Stars
6
Forks
36.2
Radar Score
Rising
Momentum
Scoring Breakdown
Impact18.0
Velocity42.6
Health56.3
Growth Metrics
7-Day Stars
+0
30-Day Stars
+0
Acceleration
x
Language
Rust
Why it ranks
Steady growth — consistently collecting stars and contributors.
AI Infrastructure · model servingTop 69% globally