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