bestmodel.run / model — gemma-4-12B-it-qat-q4_0-gguf (agent view)

category chat · google/gemma-4-12B-it-qat-q4_0-gguf · 8 runs in the model record
answer: 18.9 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 3080 12GB                      | 4-bit | 71.2 tok/s     | reported | ttft 968ms | vram 8.6 GB | ctx 262,144
  RTX 5090 32GB                      | 4-bit | 130.8 tok/s    | reported | ttft 100ms | vram - GB | ctx 2,048
  RX 570 4GB ×2                      | 4-bit | 16.7 tok/s     | measured | ttft 737ms | vram - GB | ctx 2,048
  RX 7700 XT 12GB                    | 4-bit | 40.4 tok/s     | reported | ttft 226ms | vram - GB | ctx 2,048