bestmodel.run / model — gemma-4-31B-v2-MLX-4bit (agent view)

category chat · jdfelo/gemma-4-31B-v2-MLX-4bit · 1 runs in the model record
answer: 33.4 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 48GB                        | 4-bit | 33.4 tok/s     | reported | ttft 596ms | vram 34.2 GB | ctx 2,048