C++
brontoguana/krasis
Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware
★ 526
Stars
33 forks · 19 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.
39.1
Momentum / 100
see the breakdown below
9mo ago
Created
last push 13d 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 | 15.0 | last week ran 2.48× the monthly pace |
| Freshness | 15 | 14.1 | last push 13d ago; decays to zero at 180 days |
| Scale | 15 | 7.9 | 526 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 39.1 | sum of the above |
Detail
| Topics | cpu-inferencegguf-model-supportgpu-inferencehigh-performance-inferencehybrid-inferenceinference-engineinference-optimizationlarge-language-modelsllama-cpp-alternativellm-inferencemixture-of-expertstransformer |
| Matched on | LLM & Inference (large-language-models, llm-inference) |
| Short window | +2 stars over 7 days = 0.3/day |
| Long window | +3 stars over 26 days = 0.1/day |
| Lifetime average | 1.96 stars/day over 269 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |