bestmodel.run / model — Qwen3.5-4B (agent view)

category chat · Qwen/Qwen3.5-4B · 20 runs in the model record
answer: 61 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 8745H w/ Radeon 780M   | 4-bit | 28 tok/s       | measured | ttft 1,537ms | vram 3.5 GB | ctx 65,536
  AMD Ryzen 7 8745H w/ Radeon 780M Graphics | 4-bit | 22 tok/s       | reported | ttft 961ms | vram - GB | ctx 65,536
  Intel(R) Core(TM) Ultra 7 155H     | 4-bit | 14.6 tok/s     | reported | ttft -ms | vram - GB | ctx 2,048
  GTX 1650 4GB                       | 4-bit | 30.6 tok/s     | reported | ttft 14,583ms | vram - GB | ctx 4,096
  RTX 3060 12GB                      | 4-bit | 76.5 tok/s     | measured | ttft 1,124ms | vram - GB | ctx 131,072
  RX 6700 10GB                       | 4-bit | 76.6 tok/s     | reported | ttft 2,141ms | vram 4 GB | ctx 4,096
  Ryzen AI Max 395 128GB             | 4-bit | 61.3 tok/s     | measured | ttft -ms | vram 4.3 GB | ctx 32,768
  Ultra 7 155H 32GB                  | 4-bit | 12 tok/s       | reported | ttft -ms | vram - GB | ctx 2,048