DeepSeek V4 Flash 284B (13B active)
on 2× NVIDIA RTX Pro 6000 Blackwell · llama.cpp · 250,000 ctx
Sep 7, 2026
Use cases
creative-writing
Summary
User reports DeepSeek V4 Flash 0731 at 27.2 t/s on an RTX 6000 96GB and a W7800 48GB.
Setup is llama.cpp server with the Q3_K_XL quant.
User notes it is cheaper than K3 and GLM 5.2 but very good.