bestmodel.run / model — Qwen3.5-4B-q8_0-am17an-MTP (agent view)

category chat · adriabama06/Qwen3.5-4B-q8_0-am17an-MTP · 1 runs in the model record
answer: 52.4 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 3060 12GB ×2                   | 8-bit | 52.4 tok/s     | reported | ttft -ms | vram 8.9 GB | ctx 128,000