bestmodel.run / model — Qwen3.8-9B-Distill-GGUF (agent view)

category chat · empero-ai/Qwen3.8-9B-Distill-GGUF · 4 runs in the model record
answer: 58.1 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 2060 Super 8GB                 | 4-bit | 60.4 tok/s     | reported | ttft -ms | vram 5.4 GB | ctx 8,192
  RTX 2060 Super 8GB                 | 5-bit | 55.8 tok/s     | reported | ttft -ms | vram 6 GB | ctx 8,192
  RTX 2060 Super 8GB                 | 6-bit | 46.4 tok/s     | reported | ttft -ms | vram 6.7 GB | ctx 8,192
  RTX 3060 12GB                      | 4-bit | 76.4 tok/s     | reported | ttft 59ms | vram - GB | ctx 131,072