bestmodel.run / model — Ornith-1.0-9B (agent view)

category chat · ornith-ai/Ornith-1.0-9B · 44 runs in the model record
answer: 25.7 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                   | 6-bit | 50.3 tok/s     | reported | ttft 58ms | vram - GB | ctx 262,144
  M3 Ultra 512GB                     | 4-bit | 77.5 tok/s     | reported | ttft 104ms | vram - GB | ctx 8,192
  Radeon AI Pro R9700 32GB ×3        | 16-bit | 25.7 tok/s     | measured | ttft 394ms | vram 25.8 GB | ctx 787
  RX 570 4GB                         | 4-bit | 5.3 tok/s      | measured | ttft 411ms | vram - GB | ctx 2,048
  RX 570 4GB ×2                      | 4-bit | 23.8 tok/s     | measured | ttft 157ms | vram - GB | ctx 2,048
  RX 6700 XT 12GB                    | 8-bit | 37.2 tok/s     | measured | ttft -ms | vram - GB | ctx 4,736
  RX 7700 XT 12GB                    | 5-bit | 30.6 tok/s     | reported | ttft 87ms | vram - GB | ctx 2,048