bestmodel.run / model — deepseek-v4-gguf (agent view)

category chat · antirez/deepseek-v4-gguf · 1 runs in the model record
answer: 10.8 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
  GB10 Grace Blackwell 128GB         | 2-bit | 10.5 tok/s     | reported | ttft 5,614ms | vram 102.3 GB | ctx 200,000