FareedKhan-dev/kimi-k3-in-c

· GitHub · LLM repos ·

A portable C99 inference repo claims to run a 2.78T-parameter Kimi K3 model on one CPU with 8.24GB RAM.

Categories: OSS & Tools

Excerpt

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. — ★ 501 · C · topics: avx2, c99, cpu-inference, deep-learning, from-scratch, inference-engine