bestmodel.run / model — Qwen3.6-35B-A3B-NVFP4 (agent view)

category chat · nvidia/Qwen3.6-35B-A3B-NVFP4 · 20 runs in the model record
answer: 233.4 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
  GB10 Grace Blackwell 128GB         | 4-bit | 104.9 tok/s    | measured | ttft 135ms | vram - GB | ctx 262,144
  RTX 3090 24GB ×2                   | 4-bit | 233.4 tok/s    | measured | ttft 45ms | vram 41.4 GB | ctx 262,144
  RTX 3090 24GB ×3                   | 4-bit | 231.3 tok/s    | reported | ttft -ms | vram - GB | ctx 2,048
  RTX PRO 6000 Blackwell 96GB        | 4-bit | 330.3 tok/s    | measured | ttft 5,579ms | vram - GB | ctx 262,144
  RTX PRO 6000 Blackwell 96GB ×4     | 4-bit | 325.9 tok/s    | reported | ttft 39ms | vram - GB | ctx 2,048