bestmodel.run / model — Qwen3.5-122B-A10B (agent view)

category chat · Qwen/Qwen3.5-122B-A10B · 12 runs in the model record
answer: 26.4 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 | 45.6 tok/s     | reported | ttft -ms | vram - GB | ctx 2,048
  GB10 Grace Blackwell 128GB         | 6-bit | 17.1 tok/s     | reported | ttft -ms | vram - GB | ctx 100,000
  GTX 1080 Ti 11GB                   | 3-bit | 3.2 tok/s      | reported | ttft -ms | vram 10.3 GB | ctx 8,192
  M5 Max 128GB                       | 4-bit | 50.1 tok/s     | reported | ttft 44ms | vram - GB | ctx 2,048
  Radeon AI Pro R9700 32GB ×3        | 4-bit | 26.5 tok/s     | measured | ttft 1,296ms | vram 77.1 GB | ctx 65,536
  Ryzen AI Max 395 128GB             | 4-bit | 18 tok/s       | reported | ttft 3,418ms | vram 74 GB | ctx 262,144