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

category chat · ornith-ai/Ornith-1.0-35B-GGUF · 30 runs in the model record
answer: 60.6 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 B60 24GB                   | 4-bit | 62.7 tok/s     | reported | ttft 532ms | vram - GB | ctx 4,096
  Arc Pro B60 24GB ×2                | 4-bit | 62.6 tok/s     | reported | ttft 532ms | vram - GB | ctx 4,096
  RTX 3060 12GB ×2                   | 4-bit | 85.9 tok/s     | measured | ttft 3,079ms | vram 21.1 GB | ctx 65,536
  RTX 3090 24GB                      | 4-bit | 124.1 tok/s    | reported | ttft 94ms | vram - GB | ctx 262,144
  RTX 3090 24GB ×2                   | 4-bit | 136.5 tok/s    | reported | ttft 86ms | vram - GB | ctx 262,144
  RTX 4070 12GB                      | 4-bit | 43.2 tok/s     | measured | ttft 393ms | vram - GB | ctx 2,048
  RTX 5090 32GB                      | 4-bit | 252.6 tok/s    | reported | ttft 1ms | vram - GB | ctx 2,048
  RX 5700 4GB                        | 4-bit | 27.4 tok/s     | reported | ttft 122ms | vram - GB | ctx 2,048
  RX 5700 8GB                        | 4-bit | 27.4 tok/s     | reported | ttft 127ms | vram - GB | ctx 2,048
  Ryzen AI Max 395 128GB             | 4-bit | 43 tok/s       | reported | ttft 26,649ms | vram 20.9 GB | ctx 65,536
  Ryzen AI Max 395 64GB              | 4-bit | 60.6 tok/s     | measured | ttft 1,583ms | vram 21.5 GB | ctx 8,192