bestmodel.run / model — Ornith-1.5-9B (agent view)

category chat · ornith-ai/Ornith-1.5-9B · 76 runs in the model record
answer: 73.5 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
  CMP 170HX 64GB                     | 16-bit | 72.8 tok/s     | measured | ttft 2,249ms | vram - GB | ctx 131,336
  RTX 2060 Super 8GB                 | 4-bit | 60.4 tok/s     | reported | ttft -ms | vram 5.4 GB | ctx 8,192
  RTX 5070 12GB                      | 4-bit | 102 tok/s      | reported | ttft 47ms | vram - GB | ctx 2,048
  RX 570 4GB                         | 4-bit | 23 tok/s       | measured | ttft 43,198ms | vram - GB | ctx 2,048