● Open SourceNov 8, 2026 · 17:221 source
Llama-modchip: 284B DeepSeek on 64GB RAM, no GPU
From github.com
AI;DR
Llama-modchip allows running 284B DeepSeek-V4-Flash and 30B MoEs on a 64GB CPU with no GPUs. The setup supports a 256K context window.
Read originalSign in to suggest
Sources
+ 1 more
- DISCUSSIONjoshcsimmonsnews.ycombinator.com