Repository profile

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.

  • avx2
  • c99
  • cpu-inference
  • deep-learning
  • from-scratch
  • inference-engine
  • kimi-k3
  • linear-attention
  • llm
  • llm-inference
  • machine-learning
  • memory-efficient
  • mixture-of-experts
  • moe
  • mxfp4
  • quantization
  • simd
  • systems-programming
  • transformer
  • zero-dependencies

Repository overview

Public GitHub metrics and OpenPulse observations
GitHub stars9,099
Public forks1,486
Growth · 24h+8 stars
Growth · 7dBuilding history
Growth · 30dBuilding history

Star activity

Last 7 days
16 Oct4 observed days · gaps preserved19 Oct

Observed star growth

Samples or dated GitHub history
24h +8 stars Measured from observations 18 Oct 2026 → 19 Oct 2026
7d Building history More observations needed — → 19 Oct 2026
30d Building history More observations needed — → 19 Oct 2026