bestmodel.run / model — Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4 (agent view)

category chat · sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4 · 1 runs in the model record
answer: 133.3 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 5070 Ti 16GB                   | 4-bit | 133.3 tok/s    | reported | ttft 132ms | vram - GB | ctx 35,623