This is needs ~80GB of fast memory at 4 bits per weight. Faster memory is better...

petu 33 days ago | parent | context | favorite | on: Qwen3.8-Flash-Next

This is needs ~80GB of fast memory at 4 bits per weight. Faster memory is better, but probably even something like 3090 + 64GB RAM should work (not fast, but maybe even 20-30 t/s? llama.cpp support pending).