bestmodel.run / model — Ornith-1.5-35B-A3B-GGUF (agent view)

category chat · ornith-ai/Ornith-1.5-35B-A3B-GGUF · 119 runs in the model record
answer: 104.9 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 | 131.5 tok/s    | reported | ttft 153ms | vram - GB | ctx 8,192
  CMP 170HX 64GB                     | 5-bit | 108.7 tok/s    | measured | ttft 9,275ms | vram - GB | ctx 131,338
  CMP 170HX 64GB                     | 8-bit | 104.8 tok/s    | measured | ttft 8,975ms | vram - GB | ctx 131,338
  RTX 3080 12GB                      | 4-bit | 60.8 tok/s     | reported | ttft 4,184ms | vram 9.6 GB | ctx 131,072
  RTX 4070 12GB                      | 4-bit | 33.5 tok/s     | measured | ttft 650ms | vram 10.2 GB | ctx 262,144