GitVibes daily briefing Β· 2026-11-10 Β· systems
Llama-modchip: 284B DeepSeek on 64GB RAM, no GPU
Curated by Radha
Perspective
Where is the trust boundary you would test first around βLlama-modchip: 284B DeepSeek on 64GB RAM, no GPUβ?
Source summary
π Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs). SwiGLU-H2, Stockfish-PVS L3 & 13ms Claude Code restore. - synchopate/llama-modchip
Original reporting: github.com Β· Published 2026-11-08