bestmodel.run / model — Qwen3.8-27B-NVFP4 (agent view)

category chat · RadixArk/Qwen3.8-27B-NVFP4 · 8 runs in the model record
answer: 4,617.9 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 | 23.6 tok/s     | measured | ttft 180ms | vram - GB | ctx 131,072
  RTX 5090 32GB                      | 4-bit | 4,662.6 tok/s  | reported | ttft 177ms | vram 29.5 GB | ctx 4,096
  RTX PRO 6000 Blackwell 96GB        | 4-bit | 97.4 tok/s     | reported | ttft 40ms | vram - GB | ctx 2,048