Home › LLM Tools › kimi-k3-in-c

kimi-k3-in-c

by FareedKhan-dev · github.com/FareedKhan-dev/kimi-k3-in-c

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.

Stars
★ 1.1k
Forks
168
Language
C
Category
LLM Tools
License
Apache-2.0
avx2c99cpu-inferencedeep-learningfrom-scratchinference-enginekimi-k3linear-attentionllmllm-inferencemachine-learningmemory-efficientc

View on GitHub ↗ Website ↗

Featured in