bestmodel.run / model — Qwen3-14B (agent view)

category chat · Qwen/Qwen3-14B · 20 runs in the model record
answer: 33.7 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
  M1 Max 64GB                        | 4-bit | 24.8 tok/s     | reported | ttft 51ms | vram - GB | ctx 2,048
  RTX 3060 12GB                      | 4-bit | 29 tok/s       | measured | ttft 2,553ms | vram 8.7 GB | ctx 65,536
  RTX 3080 12GB                      | 4-bit | 75 tok/s       | reported | ttft -ms | vram 8.7 GB | ctx 2,048
  RTX 3090 24GB                      | 4-bit | 42.9 tok/s     | measured | ttft 2,655ms | vram 0 GB | ctx 131,072
  RTX3060+RTX2080-pooled-20GB 20GB   | 4-bit | 35 tok/s       | reported | ttft -ms | vram 8.7 GB | ctx 2,048