kimi-k3-in-c is an open-source LLM inference tool written in C, released under the Apache-2.0 license. The repository has collected 9.1k stars and 1.5k forks; the latest push was in October 2026. Docs and downloads are linked from medium.com.
“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.”
— FareedKhan-dev, project description on GitHub
Details
| Category | Local LLMs & Inference |
|---|---|
| GitHub stars | 9,098 |
| Forks | 1,486 |
| Language | C |
| License | Apache-2.0 |
| Last updated | |
| Owner | FareedKhan-dev |
| Website | medium.com/@fareedkhandev/building-kimi-k3-in-c-to-run-a-2-8t-model-on-consumer-hardware-a5792cbf3b59 |
| Repository | FareedKhan-dev/kimi-k3-in-c |
Tags
avx2c99cpu-inferencedeep-learningfrom-scratchinference-enginekimi-k3linear-attention
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.