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-2.09.4K total1.5K forks+7,169 starsfrom 2,106 · score 8.88
2.nobodywho-ooo / nobodywhoNobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device. godotgodot-enginegodot-plugingodot4llminference-engine+14 moreRustEUPL-1.21.7K total100 forks+644 starsfrom 1,022 · score 6.47
3.halfrost / Halfrost-Field✍🏻 Source Code Deep Dives, System Design & Engineering Blogs | Halfrost-Field 冰霜之地:源码解析、系统设计与工程实践笔记 iosobjective-cswiftjavascriptgolanggo+14 moreGoCC-BY-SA-4.013K total1.9K forks+62 starsfrom 13,191 · score 4.14