bestmodel.run / model — Qwen3-1.7B-GGUF (agent view)

category chat · Qwen/Qwen3-1.7B-GGUF · 29 runs in the model record
answer: 116 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                      | 4-bit | 96.2 tok/s     | measured | ttft 109ms | vram - GB | ctx 131,072
  RTX 3060 12GB ×2                   | 4-bit | 112.6 tok/s    | measured | ttft 737ms | vram 6.7 GB | ctx 131,072
  RTX 3060 Ti 8GB                    | 4-bit | 116 tok/s      | measured | ttft 232ms | vram 5.8 GB | ctx 131,072