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

category chat · sakamakismile/Qwen3.8-27B-MTP-NVFP4 · 8 runs in the model record
answer: 117.3 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
  RTX 5090 32GB                      | 4-bit | 117.7 tok/s    | measured | ttft 815ms | vram - GB | ctx 172,800
  RTX PRO 6000 Blackwell 96GB        | 4-bit | 112.1 tok/s    | reported | ttft -ms | vram - GB | ctx 2,048