bestmodel.run / model — DeepSeek-V4-Flash-0731 (agent view)

category chat · deepseek-ai/DeepSeek-V4-Flash-0731 · 60 runs in the model record
answer: 84.8 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
  CMP 170HX 64GB ×4                  | 8-bit | 90.6 tok/s     | measured | ttft 422ms | vram - GB | ctx 487,713
  GB10 Grace Blackwell 256GB         | 8-bit | 24.9 tok/s     | measured | ttft 185ms | vram - GB | ctx 2,048
  M3 128GB                           | 2-bit | 23.3 tok/s     | reported | ttft 21ms | vram 87.1 GB | ctx 393,216
  Radeon AI Pro R9700 32GB           | 2-bit | 59.4 tok/s     | measured | ttft 2,004ms | vram 25.3 GB | ctx 131,072
  Radeon AI Pro R9700 32GB           | 4-bit | 50.5 tok/s     | reported | ttft 6,063ms | vram 28.1 GB | ctx 32,768
  Radeon AI Pro R9700 32GB ×3        | 1-bit | 37.3 tok/s     | measured | ttft 1,880ms | vram - GB | ctx 32,768
  RTX 3090 24GB ×8                   | 8-bit | 93.3 tok/s     | reported | ttft 191ms | vram 184.4 GB | ctx 327,680
  RTX PRO 6000 Blackwell 96GB ×2     | 8-bit | 257.4 tok/s    | measured | ttft 60ms | vram 94.5 GB | ctx 262,144
  RTX PRO 6000 Blackwell 96GB ×4     | 4-bit | 231.5 tok/s    | reported | ttft 50ms | vram - GB | ctx 2,048
  RTX PRO 6000 Blackwell 96GB ×4     | 8-bit | 296.7 tok/s    | measured | ttft 90ms | vram - GB | ctx 2,048
  Ryzen AI Max 395 128GB             | 1-bit | 21.8 tok/s     | reported | ttft 3,305ms | vram - GB | ctx 782
  Ryzen AI Max 395 128GB             | 2-bit | 28.3 tok/s     | reported | ttft 15,107ms | vram - GB | ctx 782