bestmodel.run / model — gemma-4-12B-coder-fable5-composer2.5-v1-GGUF (agent view)

category code · yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF · 2 runs in the model record
answer: 38.4 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 5090 32GB                      | 8-bit | 85.3 tok/s     | reported | ttft 112ms | vram - GB | ctx 2,048
  Ryzen AI Max 395 128GB             | 4-bit | 24.8 tok/s     | reported | ttft 218ms | vram 9.4 GB | ctx 4,096