bestmodel.run / model — Gemopus-4-26B-A4B-it (agent view)

category chat · Jackrong/Gemopus-4-26B-A4B-it · 4 runs in the model record
answer: 55 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
  Ryzen AI Max 395 128GB             | 4-bit | 64.2 tok/s     | reported | ttft -ms | vram 23.7 GB | ctx 128,000
  Ryzen AI Max 395 128GB             | 8-bit | 45.8 tok/s     | reported | ttft -ms | vram 33.1 GB | ctx 128,000