bestmodel.run / model — Qwen3.6-27B-AWQ-BF16-INT4 (agent view)

category chat · cyankiwi/Qwen3.6-27B-AWQ-BF16-INT4 · 5 runs in the model record
answer: 98.1 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 3090 24GB ×2                   | 4-bit | 43.2 tok/s     | reported | ttft 1,989ms | vram - GB | ctx 2,048
  RTX 3090 24GB ×4                   | 4-bit | 67.1 tok/s     | reported | ttft 575ms | vram 92.5 GB | ctx 262,144
  RTX A6000 48GB ×2                  | 4-bit | 147.4 tok/s    | reported | ttft 129ms | vram 82.4 GB | ctx 262,144