bestmodel.run / model — Qwen3.8-27B-NVFP4-BF16-LMHead (agent view)

category chat · RadixArk/Qwen3.8-27B-NVFP4-BF16-LMHead · 10 runs in the model record
answer: 189.6 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 | 24.6 tok/s     | measured | ttft 202ms | vram - GB | ctx 131,072
  RTX 5090 32GB ×2                   | 4-bit | 223.6 tok/s    | measured | ttft 37ms | vram 57.3 GB | ctx 262,144
  RTX PRO 6000 Blackwell 96GB        | 4-bit | 296 tok/s      | reported | ttft 47ms | vram - GB | ctx 262,144