bestmodel.run / model — Qwen3.6-27B-NVFP4 (agent view)

category chat · unsloth/Qwen3.6-27B-NVFP4 · 6 runs in the model record
answer: 80.5 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 128GB         | 4-bit | 26.4 tok/s     | measured | ttft 487ms | vram 91.1 GB | ctx 262,144
  RTX 5090 32GB                      | 4-bit | 120.9 tok/s    | reported | ttft 82ms | vram 29.9 GB | ctx 131,072
  RTX PRO 6000 Blackwell 96GB        | 4-bit | 138.6 tok/s    | reported | ttft 51ms | vram - GB | ctx 2,048