bestmodel.run / model — Bonsai-27B-gguf (agent view)

category chat · prism-ml/Bonsai-27B-gguf · 40 runs in the model record
answer: 30.7 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
  RTX 3060 12GB ×2                   | 4-bit | 29.3 tok/s     | measured | ttft 1ms | vram 21.9 GB | ctx 262,144
  RTX 3080 12GB                      | 1-bit | 72.9 tok/s     | reported | ttft 2,054ms | vram 5.1 GB | ctx 32,768
  RTX 3090 24GB                      | 1-bit | 39.8 tok/s     | measured | ttft 31,904ms | vram 5.6 GB | ctx 262,144
  RTX 5090 32GB                      | 1-bit | 136.7 tok/s    | reported | ttft 82ms | vram - GB | ctx 2,048
  RX 570 4GB                         | 1-bit | 12.8 tok/s     | measured | ttft 53,010ms | vram - GB | ctx 2,048
  RX 7700 XT 12GB                    | 1-bit | 44 tok/s       | reported | ttft 117ms | vram - GB | ctx 2,048
  Ryzen AI Max 395 128GB             | 1-bit | 33.6 tok/s     | measured | ttft 26,241ms | vram - GB | ctx 262,144