bestmodel.run / model — Qwen3.6-27B (agent view)

category chat · unsloth/Qwen3.6-27B · 41 runs in the model record
answer: 27.5 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
  Arc Pro B70 32GB ×2                | 4-bit | 42.1 tok/s     | reported | ttft -ms | vram - GB | ctx 512
  Arc Pro B70 32GB ×3                | 4-bit | 49.4 tok/s     | measured | ttft -ms | vram - GB | ctx 2,048
  Arc Pro B70 32GB ×4                | 4-bit | 39.2 tok/s     | measured | ttft -ms | vram - GB | ctx 1,024
  M3 Ultra 512GB                     | 4-bit | 26.3 tok/s     | measured | ttft 316ms | vram - GB | ctx 8,192
  M3 Ultra 512GB                     | 8-bit | 18.5 tok/s     | reported | ttft 574ms | vram - GB | ctx 8,192
  M4 Max 48GB                        | 4-bit | 21.8 tok/s     | reported | ttft 1ms | vram - GB | ctx 4,096
  RTX 3090 24GB ×2                   | 4-bit | 41.2 tok/s     | measured | ttft 346ms | vram 24.3 GB | ctx 131,712
  RTX 3090 24GB ×2                   | 8-bit | 45.5 tok/s     | reported | ttft 804ms | vram 19 GB | ctx 8,192
  RTX 3090 Ti 24GB                   | 4-bit | 155.9 tok/s    | reported | ttft 68ms | vram 18.4 GB | ctx 4,096
  RTX 4090 24GB                      | 3-bit | 49.4 tok/s     | reported | ttft 163ms | vram - GB | ctx 8,192
  Ryzen AI Max 395 128GB             | 4-bit | 12 tok/s       | measured | ttft -ms | vram 24 GB | ctx 65,536
  Ryzen AI Max 395 128GB             | 8-bit | 6.4 tok/s      | measured | ttft -ms | vram 39.3 GB | ctx 32,768