bestmodel.run / model — gemma-3-text-4b-it-4bit (agent view)

category chat · mlx-community/gemma-3-text-4b-it-4bit · 2 runs in the model record
answer: 140.1 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 Max 128GB                       | 4-bit | 175.1 tok/s    | reported | ttft -ms | vram 3 GB | ctx 2,048
  Pro 64GB                           | 4-bit | 105 tok/s      | reported | ttft 109ms | vram 3 GB | ctx 2,048