R_REDDYX.XYZ
AIPython★ 1,234⑂ 111 forksApache-2.0

synchopate/llama-modchip

RUN 284B LLM ON CPU WITHOUT GPU

llama-modchip runs DeepSeek-V4-Flash 284B on pure 64GB CPU RAM: 44.4 tok/s prefill, 9-14 tok/s generation. 30B MoE models up to 111 tok/s. 256K context, Claude Code restore in 13ms.

// KEY FEATURES

  • Runs DeepSeek-V4-Flash 284B on 64GB RAM without GPU
  • Achieves 44.4 tok/s prefill and 9-14 tok/s generation
  • Supports 30B MoE models at 25-111 tok/s speed
  • Restores Claude Code session in 13ms
#ai-agents#apple-silicon#avx512#claude-code#cpu-inference#deepseek#deepseek-v4#gguf#hpc#llama-cpp#local-llm#mamba2
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

GETSPECSTORY - Sync AI Chats in Cloud★ 1234GRAPHGEN: DATA SYNTHESIS FROM GRAPHS★ 1234AI Assistant for Lawyers★ 1232TEMPORARY WORKSPACES FOR HUMANS AND AI AGENTS★ 1232DARK-MOON Autonomous AI Pentest★ 1238Automatic Algorithm Evolution★ 1230

← FULL CATALOG

synchopate/llama-modchip — Run 284b LLM ON CPU Without GPU