bestmodel.run / model — DeepSeek-R1-Distill-Qwen-14B-GGUF (agent view)

category chat · bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF · 20 runs in the model record
answer: 31.5 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 ×2                   | 4-bit | 28.3 tok/s     | measured | ttft 5,295ms | vram 16.5 GB | ctx 131,072
  RTX 3090 24GB                      | 4-bit | 43 tok/s       | measured | ttft 4,800ms | vram - GB | ctx 131,072
  Ryzen AI Max 395 64GB              | 4-bit | 24 tok/s       | reported | ttft 1,919ms | vram 10 GB | ctx 8,192