bestmodel.run / model — gemma-4-E4B-it-qat-q4_0-gguf (agent view)

category chat · google/gemma-4-E4B-it-qat-q4_0-gguf · 4 runs in the model record
answer: 84 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 3060 12GB                      | 4-bit | 88.1 tok/s     | reported | ttft 1,371ms | vram 4.9 GB | ctx 4,608
  RTX 5070 12GB                      | 4-bit | 152.7 tok/s    | reported | ttft 60ms | vram - GB | ctx 32,768
  RX 570 4GB                         | 4-bit | 27.5 tok/s     | reported | ttft 326ms | vram - GB | ctx 2,048
  RX 570 4GB ×2                      | 4-bit | 33.2 tok/s     | reported | ttft 242ms | vram - GB | ctx 2,048