C · GPL-3.0
prabanta-dev/janas
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
★ 584
Stars
51 forks · 22 open issues
+16/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
46.5
Momentum / 100
see the breakdown below
48d ago
Created
last push 4d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 23.6 | +16/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.97× the monthly pace |
| Freshness | 15 | 14.8 | last push 4d ago; decays to zero at 180 days |
| Scale | 15 | 8.0 | 584 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 46.5 | sum of the above |
Detail
| Topics | avx2ccpu-inferenceggufinference-enginelinuxllmlocal-llmmixture-of-expertsmoenvmequantizationqwen3simdspeculative-decodingvulkan |
| Matched on | LLM & Inference (llm) |
| Short window | +113 stars over 7 days = 16.1/day |
| Long window | +382 stars over 23 days = 16.6/day |
| Lifetime average | 12.67 stars/day over 46 days |
| First seen here | 2026-10-13 |
| Last read | 4d ago |