bestmodel.run / model — DeepSeek-V4.1-Flash (agent view)

category chat · deepseek-ai/DeepSeek-V4.1-Flash · 13 runs in the model record
answer: 72 tok/s (model median)

Honesty ladder: measured > reported > extrapolated > formula > no data yet.
Empty fields stay empty — never filled with an estimate.

  rig | quant | median result | basis | ttft | peak vram | max context
  GB10 Grace Blackwell 512GB         | 4-bit | 59.1 tok/s     | measured | ttft 391ms | vram - GB | ctx 430,080
  GB10 Grace Blackwell 512GB         | 8-bit | 31.7 tok/s     | reported | ttft 3,328ms | vram - GB | ctx 2,048
  RTX PRO 6000 Blackwell Max-Q Workstation Edition 96GB ×4 | 8-bit | 303.7 tok/s    | measured | ttft 221ms | vram - GB | ctx 524,288