bestmodel.run / model — granite-4.2-8b-GGUF (agent view)

category chat · ibm-granite/granite-4.2-8b-GGUF · 3 runs in the model record
answer: 53.6 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 | 55.3 tok/s     | reported | ttft 315ms | vram 6.4 GB | ctx 4,096
  RTX 3060 12GB                      | 5-bit | 52.5 tok/s     | reported | ttft 318ms | vram 6.6 GB | ctx 4,096