Back to Tools Directory
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.
Categories & Topics
avx2c99cpu-inferencedeep-learningfrom-scratchinference-enginekimi-k3linear-attentionllmllm-inferencemachine-learningmemory-efficientmixture-of-expertsmoemxfp4quantizationsimdsystems-programmingtransformerzero-dependencies
Repository Stats
10k
GitHub Stars
1.7k
Forks
10k
Watchers
27
Open Issues
License
Apache License 2.0
Repository
FareedKhan-dev/kimi-k3-in-cLast Updated
Today
November 5, 2026
Latest Release
v1.1.0
1 months ago
![dependabot[bot]](https://avatars.githubusercontent.com/in/29110?v=4)
Related Tools
auto-deep-researcher-24x7
1.1k
🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.
Confucius4-TTS
853
Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine
how-to-train-your-gpt
4.2k
Build a modern LLM from scratch. Every line commented. Explained like we are five.
kairos
3.2k
Official code for world model Kairos
kairos-sensenova
3.2k
Official code for world model Kairos
MatAnyone2
935
[CVPR 2026 Highlight] MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator