bestmodel.run / model — Qwen3.5-0.8B (agent view)

category chat · Qwen/Qwen3.5-0.8B · 14 runs in the model record
answer: 445.7 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
  AMD Ryzen 7 7840HS                 | 4-bit | 77.8 tok/s     | reported | ttft -ms | vram - GB | ctx 2,048
  Radeon AI Pro R9700 32GB           | 4-bit | 562.2 tok/s    | measured | ttft 44ms | vram - GB | ctx 128
  RTX 3060 12GB                      | 4-bit | 209.8 tok/s    | reported | ttft 59ms | vram - GB | ctx 4,096
  RTX 3060 12GB                      | 8-bit | 242.8 tok/s    | reported | ttft 433ms | vram 3 GB | ctx 4,608
  RTX 5060 Ti 16GB                   | 4-bit | 280.9 tok/s    | reported | ttft 48ms | vram - GB | ctx 4,096
  RTX PRO 6000 Blackwell 96GB        | 16-bit | 778.4 tok/s    | reported | ttft 37ms | vram - GB | ctx 2,048
  RX 5700 XT 8GB                     | 4-bit | 273.6 tok/s    | reported | ttft 347ms | vram - GB | ctx 128
  RX 6900 XT 16GB                    | 4-bit | 346.1 tok/s    | reported | ttft 81ms | vram - GB | ctx 128
  RX 7900 XTX 24GB                   | 4-bit | 550.2 tok/s    | reported | ttft 69ms | vram - GB | ctx 128
  RX 9070 XT 16GB                    | 4-bit | 545.3 tok/s    | reported | ttft 67ms | vram - GB | ctx 128
  Ryzen AI Max 395 103GB             | 4-bit | 291.4 tok/s    | reported | ttft 69ms | vram - GB | ctx 128