FareedKhan-dev/kimi-k3-in-c

★11,661C🌐 ElsewhereApache-2.0⑂ 1,808Issue 2Updated Oct 2, 2026

View on GitHub ↗Website ↗

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.

2.78T-parameter Kimi K3 inference in 176 KB of C, no GPU needed — This project runs the 2.78-trillion-parameter Kimi K3 model on a single CPU with only 8.24 GB peak RAM, using a 176 KB portable C99 engine with no BLAS or framework dependency. It streams the 1.56 TB checkpoint from disk, so more memory just speeds up inference rather than being required to run it at all. Useful for anyone curious about running huge MoE/transformer models on ordinary hardware.

Metrics

Retention can be computed 30 days after a repository first trends (it isn't shown until then). See About for how each metric is defined.

Star growth and Trending appearances (last 30 days)

Created Aug 1, 2026 · First on trending Nov 5, 2026

Where it's being discussed

Posts that are about this repository. Japan means Japanese-language tech media and videos; it says nothing about how widely the project is used in Japan.

Other notable repositories in the same category (LLMs & ML)

• snap-stanford/memorillaCompressing Entire Document Collections into 16 Memory Tokens
• kerlenton/bootgptA Tiny Neural Net That Boots Straight From the MBR
• scienthoon/jev-ood-calibrationTesting Whether Jev's Confidence Scores Stay Honest Out-of-Distribution
• alejandrohdez00/alien-space-of-scienceSampling research ideas that are coherent but hard for humans to reach
• microsoft/VibeVoiceMicrosoft's open voice AI grows into streaming speech recognition

See all LLMs & ML repositories →

Rank within deep-learning

See all deep-learning repositories →