bestmodel.run / model — Qwen3.8-27B-5090-goldilocks-GGUF (agent view)

category chat · Rabbit-Hole-Ai/Qwen3.8-27B-5090-goldilocks-GGUF · 1 runs in the model record
answer: 93.5 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 5090 32GB                      | 6-bit | 93.5 tok/s     | reported | ttft 279ms | vram 29.8 GB | ctx 131,000