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

category chat · fraserprice/DeepSeek-V4-Flash-Abliterated · 2 runs in the model record
answer: 199.4 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
  RTX PRO 6000 Blackwell 96GB ×2     | 8-bit | 181.3 tok/s    | reported | ttft 45ms | vram - GB | ctx 2,048
  RTX PRO 6000 Blackwell 96GB ×4     | 8-bit | 217.5 tok/s    | reported | ttft 42ms | vram - GB | ctx 2,048