bestmodel.run / model — gemma-4-E4B-it-OBLITERATED (agent view)

category chat · OBLITERATUS/gemma-4-E4B-it-OBLITERATED · 3 runs in the model record
answer: 27.2 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
  GTX 1060 3GB ×2                    | 4-bit | 27.2 tok/s     | reported | ttft -ms | vram 4.6 GB | ctx 2,048
  Radeon RX 9060 XT 16GB             | 8-bit | 53.9 tok/s     | reported | ttft 1,581ms | vram 5.3 GB | ctx 4,096
  RX 570 4GB ×2                      | 4-bit | 26.6 tok/s     | reported | ttft 447ms | vram - GB | ctx 2,048