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

category chat · unsloth/Qwen3.6-27B-MTP-GGUF · 161 runs in the model record
answer: 66.4 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 | 30.7 tok/s     | reported | ttft 500ms | vram - GB | ctx 4,096
  Arc Pro B70 32GB                   | 8-bit | 36.1 tok/s     | reported | ttft 785ms | vram - GB | ctx 32,768
  M5 Pro 24GB                        | 2-bit | 21.5 tok/s     | reported | ttft 150ms | vram - GB | ctx 2,048
  M5 Pro 24GB                        | 3-bit | 20 tok/s       | reported | ttft 164ms | vram - GB | ctx 2,048
  M5 Pro 24GB                        | 4-bit | 18.2 tok/s     | measured | ttft 175ms | vram - GB | ctx 2,048
  Radeon AI Pro R9700 32GB           | 4-bit | 43.3 tok/s     | reported | ttft 77ms | vram - GB | ctx 2,048
  RTX 3060 12GB ×2                   | 4-bit | 17.7 tok/s     | measured | ttft 7,257ms | vram 18.1 GB | ctx 131,072
  RTX 3090 24GB                      | 1-bit | 49.2 tok/s     | measured | ttft -ms | vram 2.5 GB | ctx 196,608
  RTX 3090 24GB                      | 4-bit | 101.5 tok/s    | measured | ttft 761ms | vram 20.2 GB | ctx 131,072
  RTX 3090 24GB ×2                   | 4-bit | 65.2 tok/s     | measured | ttft 497ms | vram - GB | ctx 262,144
  RTX 4090 24GB                      | 4-bit | 94.1 tok/s     | reported | ttft -ms | vram 23.9 GB | ctx 76,000
  RTX 5060 Ti 16GB                   | 3-bit | 26.7 tok/s     | reported | ttft 596ms | vram - GB | ctx 2,048
  RTX 5060 Ti 16GB ×2                | 4-bit | 33.3 tok/s     | reported | ttft 179ms | vram 19.3 GB | ctx 65,536
  RTX 5090 32GB                      | 5-bit | 70.4 tok/s     | reported | ttft 141ms | vram - GB | ctx 2,048
  RTX PRO 6000 Blackwell 96GB        | 6-bit | 60.1 tok/s     | reported | ttft 301ms | vram - GB | ctx 131,072
  RTX PRO 6000 Blackwell 96GB        | 16-bit | 40.3 tok/s     | reported | ttft 282ms | vram - GB | ctx 131,072
  RX 7900 XTX 24GB                   | 4-bit | 48.5 tok/s     | measured | ttft 1,359ms | vram 21.9 GB | ctx 262,144
  Ryzen AI Max 395 128GB             | 4-bit | 17.1 tok/s     | measured | ttft 29,410ms | vram 21.2 GB | ctx 65,536
  Ryzen AI Max 395 64GB              | 4-bit | 29.2 tok/s     | measured | ttft 4,063ms | vram 18.3 GB | ctx 8,192