bestmodel.run / model — DeepSeek-V4-Flash-180B (agent view)

category chat · 0xSero/DeepSeek-V4-Flash-180B · 35 runs in the model record
answer: 40.2 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
  Arc Pro B70 32GB ×4                | 8-bit | 41 tok/s       | measured | ttft 330ms | vram - GB | ctx 1,024
  GB10 Grace Blackwell 128GB         | 8-bit | 23.3 tok/s     | reported | ttft 2,481ms | vram 105.7 GB | ctx 200,000