bestmodel.run / model — Qwen3-0.6B-GGUF (agent view)

category chat · Qwen/Qwen3-0.6B-GGUF · 36 runs in the model record
answer: 117.5 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 | 117.5 tok/s    | measured | ttft 63ms | vram - GB | ctx 131,072
  RTX 3060 12GB ×2                   | 4-bit | 144.4 tok/s    | measured | ttft 518ms | vram 6.1 GB | ctx 131,072
  RTX PRO 6000 Blackwell 96GB        | 4-bit | 956.4 tok/s    | reported | ttft -ms | vram 1.1 GB | ctx 640