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.
- avx2
- c99
- cpu-inference
- deep-learning
132,241 visible repositories in the index
1–12 of 12 · Most stars
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.
Modern, secure, portable, multiprotocol bootloader and boot manager.
Pure C inference of Mistral Voxtral Realtime 4B speech to text model
Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)
Automatically exported from code.google.com/p/word2vec
Tutel MoE: Optimized Mixture-of-Experts Library, Support GLM/Kimi/Gpt/DeepSeek/Qwen using FP8/NVFP4/MXFP4
The simplest and lowest-cost AI integration solution. If you like this project, please give it a Star~ | 最简单、最低成本的AI接入方案。喜欢本项目的话点个 Star 吧~
The most atomic way to train and inference a GPT in pure, dependency-free C
lightweight system-level observability for AI Agents
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
Local LLM, image&video&music generator
A minimal, fast, graphical UEFI boot manager written in C. no external dependencies — just a config file :)