bestmodel.run / model — Qwen3.6-27B-DFlash (agent view)

category chat · z-lab/Qwen3.6-27B-DFlash · 10 runs in the model record
answer: 39.2 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 ×2                | 4-bit | 38.2 tok/s     | measured | ttft -ms | vram - GB | ctx 512
  Arc Pro B70 32GB ×3                | 4-bit | 41.4 tok/s     | measured | ttft -ms | vram - GB | ctx 512
  Arc Pro B70 32GB ×4                | 4-bit | 31.5 tok/s     | reported | ttft -ms | vram - GB | ctx 512
  GB10 Grace Blackwell 128GB         | 8-bit | 62.1 tok/s     | reported | ttft 1ms | vram - GB | ctx 2,048
  RTX 5090 32GB                      | 4-bit | 215.4 tok/s    | reported | ttft 470ms | vram 23 GB | ctx 1,024