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

category chat · ggml-org/gemma-4-12B-it-GGUF · 5 runs in the model record
answer: 57 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 3090 24GB                      | 4-bit | 57 tok/s       | measured | ttft 951ms | vram - GB | ctx 2,048
  RTX 5070 12GB                      | 4-bit | 72.1 tok/s     | reported | ttft 161ms | vram - GB | ctx 2,048