bestmodel.run / model — Qwen3.6-35B-A3B (agent view)

category chat · unsloth/Qwen3.6-35B-A3B · 16 runs in the model record
answer: 57.6 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
  M3 Ultra 512GB                     | 3-bit | 84.6 tok/s     | reported | ttft 224ms | vram - GB | ctx 8,192
  Radeon RX 7900 XTX 24GB            | 3-bit | 104.5 tok/s    | reported | ttft -ms | vram 15.7 GB | ctx 640
  RTX 3090 24GB                      | 4-bit | 91.8 tok/s     | reported | ttft 115ms | vram 21.9 GB | ctx 32,768
  RTX 4060 Ti 16GB                   | 3-bit | 60.2 tok/s     | reported | ttft 4,000ms | vram - GB | ctx 262,144
  RTX 4070 12GB                      | 4-bit | 57.4 tok/s     | measured | ttft 68ms | vram 11.6 GB | ctx 131,072
  Ryzen AI Max 395 128GB             | 4-bit | 57.5 tok/s     | measured | ttft -ms | vram 27.9 GB | ctx 131,072
  Ryzen AI Max 395 128GB             | 8-bit | 52.8 tok/s     | measured | ttft -ms | vram 40.4 GB | ctx 128,000