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.

Stars

9,434 stars

Forks

1,531 forks

Language

C

License

APACHE-2.0

Created

Aug 1, 2026

Last push

Oct 2, 2026

Updated

Nov 2, 2026

• avx2
• c99
• cpu-inference
• deep-learning
• from-scratch
• inference-engine
• kimi-k3
• linear-attention
• llm
• llm-inference
• machine-learning
• memory-efficient
• mixture-of-experts
• moe
• mxfp4
• quantization
• simd
• systems-programming
• transformer
• zero-dependencies

Admitted to the Repository Index on Oct 23, 2026: +116 stars in 7 days.