1.FareedKhan-dev / kimi-k3-in-cA 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.avx2c99cpu-inferencedeep-learningfrom-scratchinference-engine+14 moreCAPACHE-2.010K total1.6K forks+1,055 starsfrom 9,220 · score 6.96
2.antirez / ds4DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCmCMIT24K total2.4K forks+101 starsfrom 24,131 · score 4.62
3.karpathy / llama2.cInference Llama 2 in one file of pure CCMIT20K total2.7K forks+28 starsfrom 20,224 · score 3.37
4.eunomia-bpf / agentsightlightweight system-level observability for AI AgentsagentebpfllmobservabilityCMIT771 total118 forks+9 starsfrom 762 · score 2.30