C · Apache-2.0
FareedKhan-dev/kimi-k3-in-c
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
★ 10.6k
Stars
1.7k forks · 26 open issues
+203/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
83.0
Momentum / 100
see the breakdown below
3mo ago
Created
last push 37d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 44.2 | +203/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 15.0 | last week ran 3.16× the monthly pace |
| Freshness | 15 | 12.1 | last push 37d ago; decays to zero at 180 days |
| Scale | 15 | 11.7 | 10.6k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 83.0 | sum of the above |
Detail
| Topics | avx2c99cpu-inferencedeep-learningfrom-scratchinference-enginekimi-k3linear-attentionllmllm-inferencemachine-learningmemory-efficientmixture-of-expertsmoemxfp4quantizationsimdsystems-programmingtransformerzero-dependencies |
| Matched on | LLM & Inference (llm, llm-inference) |
| Short window | +1.4k stars over 7 days = 203.0/day |
| Long window | +1.7k stars over 26 days = 64.3/day |
| Lifetime average | 110.77 stars/day over 96 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |