bestmodel.run / model — Qwen3.5-9B-AWQ-4bit (agent view)

category chat · cyankiwi/Qwen3.5-9B-AWQ-4bit · 9 runs in the model record
answer: 68.4 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                   | 4-bit | 79.1 tok/s     | measured | ttft 6,060ms | vram 19.6 GB | ctx 131,072