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

category chat · unsloth/gemma-4-E4B-it-GGUF · 35 runs in the model record
answer: 68.8 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
  Minisforum UM790 Pro 64GB          | 4-bit | 21.7 tok/s     | reported | ttft -ms | vram - GB | ctx 2,048
  Radeon 890M 32GB                   | 4-bit | 18.7 tok/s     | reported | ttft 1,350ms | vram - GB | ctx 2,048
  RTX 2080 Ti 11GB                   | 4-bit | 106 tok/s      | reported | ttft -ms | vram - GB | ctx 2,048
  RTX 2080 Ti 11GB                   | 6-bit | 89 tok/s       | reported | ttft -ms | vram - GB | ctx 2,048
  RTX 2080 Ti 11GB                   | 8-bit | 80 tok/s       | reported | ttft -ms | vram - GB | ctx 2,048
  RTX 3050 8GB                       | 5-bit | 46.4 tok/s     | reported | ttft 169ms | vram - GB | ctx 128,000
  RTX 3060 12GB                      | 4-bit | 69.9 tok/s     | measured | ttft 1,066ms | vram 3.5 GB | ctx 131,072
  RTX 3060 12GB ×2                   | 4-bit | 69.3 tok/s     | measured | ttft 5,185ms | vram 5.3 GB | ctx 131,072
  Ryzen AI Max 385 24GB              | 4-bit | 18.7 tok/s     | reported | ttft 1,350ms | vram - GB | ctx 2,048