bestmodel.run / model — gemma-4-31B-it-qat-GGUF (agent view)

category chat · unsloth/gemma-4-31B-it-qat-GGUF · 2 runs in the model record
answer: 22.5 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
  M5 Pro 24GB                        | 4-bit | 27.8 tok/s     | reported | ttft 691ms | vram - GB | ctx 8,192
  RTX 5090 32GB                      | 4-bit | 207.6 tok/s    | reported | ttft 78ms | vram 30.2 GB | ctx 200,000