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

category chat · Qwen/Qwen2.5-7B-Instruct · 4 runs in the model record
answer: 53.2 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
  GTX 1080 Ti 11GB                   | 4-bit | 57.6 tok/s     | reported | ttft -ms | vram 7.4 GB | ctx 8,192
  GTX 1080 Ti 11GB                   | 5-bit | 41.1 tok/s     | reported | ttft -ms | vram 8.1 GB | ctx 8,192
  M1 Max 64GB                        | 4-bit | 48.7 tok/s     | reported | ttft 30ms | vram - GB | ctx 2,048
  RTX 4070 SUPER 12GB                | 4-bit | 77.4 tok/s     | reported | ttft 248ms | vram 7 GB | ctx 65,536