bestmodel.run / model — DeepSeek-V4-Flash-0731-GGUF (agent view)

category chat · unsloth/DeepSeek-V4-Flash-0731-GGUF · 7 runs in the model record
answer: 33.9 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 3090 24GB ×4                   | 2-bit | 41 tok/s       | reported | ttft 18,774ms | vram 90.3 GB | ctx 131,072
  RTX 3090 24GB ×7                   | 4-bit | 42.4 tok/s     | reported | ttft 916ms | vram 146.5 GB | ctx 262,144
  RTX 5090 32GB                      | 1-bit | 17.8 tok/s     | reported | ttft 250ms | vram - GB | ctx 2,048
  RTX 5090 32GB                      | 8-bit | 10.4 tok/s     | reported | ttft 271ms | vram - GB | ctx 2,048