bestmodel.run / model — Qwopus3.5-27B-v3 (agent view)

category chat · Jackrong/Qwopus3.5-27B-v3 · 25 runs in the model record
answer: 12.9 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
  RTX 3090 24GB                      | 4-bit | 25.8 tok/s     | measured | ttft 7,951ms | vram 0 GB | ctx 131,072
  RX 570 4GB                         | 4-bit | 22.8 tok/s     | reported | ttft 47,348ms | vram - GB | ctx 2,048
  Ryzen AI Max 395 128GB             | 4-bit | 12.9 tok/s     | measured | ttft -ms | vram 17.5 GB | ctx 32,768
  Ryzen AI Max 395 128GB             | 5-bit | 11.3 tok/s     | measured | ttft -ms | vram 19.9 GB | ctx 32,768
  Ryzen AI Max 395 128GB             | 6-bit | 9.9 tok/s      | reported | ttft -ms | vram 23.5 GB | ctx 32,768
  Ryzen AI Max 395 128GB             | 8-bit | 7.9 tok/s      | reported | ttft -ms | vram 29.2 GB | ctx 32,768