bestmodel.run / model — gemma-4-26B-A4B-it-qat-GGUF (agent view)

category chat · unsloth/gemma-4-26B-A4B-it-qat-GGUF · 42 runs in the model record
answer: 95.3 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
  M1 Max 64GB                        | 4-bit | 76.4 tok/s     | reported | ttft 50ms | vram - GB | ctx 2,048
  M5 Pro 24GB                        | 4-bit | 121.6 tok/s    | reported | ttft 147ms | vram - GB | ctx 2,048
  RTX 3050 8GB                       | 4-bit | 38 tok/s       | reported | ttft 952ms | vram - GB | ctx 28,000
  RTX 3060 12GB ×2                   | 4-bit | 87.8 tok/s     | measured | ttft 2,379ms | vram 16 GB | ctx 131,072
  RTX 3090 24GB                      | 4-bit | 138.3 tok/s    | measured | ttft 3,433ms | vram 0 GB | ctx 131,072