bestmodel.run / model — Qwen2.5-Coder-7B-Instruct (agent view)

category code · Qwen/Qwen2.5-Coder-7B-Instruct · 6 runs in the model record
answer: 112.5 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
  RTX 2080 8GB                       | 4-bit | 93 tok/s       | reported | ttft -ms | vram 4.7 GB | ctx 2,048
  RTX 3060 12GB                      | 4-bit | 119 tok/s      | reported | ttft -ms | vram 4.7 GB | ctx 2,048
  RTX 3080 12GB                      | 4-bit | 140.8 tok/s    | measured | ttft -ms | vram 8.2 GB | ctx 2,048
  RTX3060+RTX2080-pooled-20GB 20GB   | 4-bit | 106 tok/s      | reported | ttft -ms | vram 4.7 GB | ctx 2,048