bestmodel.run / model — Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4 (agent view)

category chat · AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4 · 7 runs in the model record
answer: 33.5 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
  GB10 Grace Blackwell 128GB         | 4-bit | 33.5 tok/s     | measured | ttft 13,000ms | vram 108 GB | ctx 256,000
  RTX 5090 32GB                      | 4-bit | 56.7 tok/s     | measured | ttft -ms | vram - GB | ctx 65,536