Dev7d ago

Kimi K3 in C

Own Kimi K3 in C?

Verify your site to claim this listing and get emailed the moment a buyer's looking for something like it.

This is mine — claim it

A minimal C99 inference engine for running the Kimi K3 model on CPU with 8GB of RAM by loading routed experts from NVMe on demand.

F

FareedKhan557

Maker

Mentioned in the wild

Alternatives

runNburnA Rust inference engine that runs quantized GGUF models larger than your RAM and VRAM by keeping weights file-backed and loading them on demand through optimized I/O.