R_REDDYX.XYZ
AIC★ 12,109⑂ 1,872 forksApache-2.0

FareedKhan-dev/kimi-k3-in-c

KIMI K3: 2.78 Trillion Parameters

Running the Kimi K3 model with 2.78 trillion parameters on a single CPU, using only 8.24 GB of RAM without BLAS, frameworks, or GPU.

// KEY FEATURES

  • Portable C99 code with no dependencies
  • Inference on a single CPU using 8.24 GB RAM
  • 2.78 trillion parameters, no GPU and BLAS
#avx2#c99#cpu-inference#deep-learning#from-scratch#inference-engine#kimi-k3#linear-attention#llm#llm-inference#machine-learning#memory-efficient
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

Agentic First CRM★ 12097Conversational AI Builder★ 12124KUBESHARK NETWORK OBSERVABILITY K8S★ 12139E2B environment for agents★ 12163AI Film Production Platform★ 12163OKTOP: Smart AI Assistant Self-Host★ 12054

← FULL CATALOG

FareedKhan-dev/kimi-k3-in-c — KIMI K3: 2.78 Trillion…