bestmodel.run / model — Ornith-1.0-35B (agent view)

category chat · ornith-ai/Ornith-1.0-35B · 12 runs in the model record
answer: 71.8 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
  Arc Pro B70 32GB                   | 4-bit | 74.3 tok/s     | reported | ttft 73ms | vram - GB | ctx 262,144
  Arc Pro B70 32GB                   | 5-bit | 69.3 tok/s     | measured | ttft -ms | vram - GB | ctx 262,144
  M3 Ultra 512GB                     | 4-bit | 89.1 tok/s     | reported | ttft 111ms | vram - GB | ctx 8,192
  Radeon AI Pro R9700 32GB ×3        | 8-bit | 74 tok/s       | reported | ttft 366ms | vram 42.9 GB | ctx 787
  Ryzen AI Max 395 128GB             | 8-bit | 54.1 tok/s     | reported | ttft 1,244ms | vram - GB | ctx 787
  Ryzen AI Max 395 64GB              | 4-bit | 60.6 tok/s     | measured | ttft 970ms | vram 21.4 GB | ctx 8,192