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

category chat · TeichAI/Qwen3.8-27B-Fable-Distill-GGUF · 3 runs in the model record
answer: 41.2 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
  RX 7900 XTX 24GB ×2                | 4-bit | 41.2 tok/s     | measured | ttft 177ms | vram - GB | ctx 2,048