FareedKhan-dev/kimi-k3-in-c · AI Repo StatsFAFareedKhan-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.
Suy luận & chạy LLM cục bộC Apache-2.0 1.8Ktạo 2026-08-01 #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