bestmodel.run / model — Qwen3.6-27B-int4-AutoRound (agent view)

category chat · Lorbus/Qwen3.6-27B-int4-AutoRound · 21 runs in the model record
answer: 66.4 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
  Arc Pro B70 32GB                   | 4-bit | 41.3 tok/s     | measured | ttft -ms | vram - GB | ctx 4,096
  Arc Pro B70 32GB ×2                | 4-bit | 48.3 tok/s     | measured | ttft -ms | vram - GB | ctx 4,096
  RTX 3090 24GB                      | 4-bit | 74.5 tok/s     | measured | ttft 480ms | vram 22.5 GB | ctx 32,768
  RTX 3090 24GB ×2                   | 4-bit | 78.2 tok/s     | measured | ttft 79ms | vram 22.8 GB | ctx 262,144
  RTX 4090 24GB                      | 16-bit | 52.6 tok/s     | reported | ttft 88ms | vram - GB | ctx 2,048
  RTX 5060 Ti 16GB ×2                | 4-bit | 69.3 tok/s     | reported | ttft 94ms | vram - GB | ctx 2,048