bestmodel.run / model — SuperDeepseek-V4-Flash-abliterated-MQ-2xDGX (agent view)

category chat · Jiunsong/SuperDeepseek-V4-Flash-abliterated-MQ-2xDGX · 2 runs in the model record
answer: 68.3 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
  GB10 Grace Blackwell 256GB         | 4-bit | 37.3 tok/s     | reported | ttft -ms | vram - GB | ctx 2,048
  GB10 Grace Blackwell 256GB         | 8-bit | 36.3 tok/s     | reported | ttft -ms | vram - GB | ctx 2,048