bestmodel.run / model — DeepSeek-V4-Flash-2bit-DQ (agent view)

category chat · mlx-community/DeepSeek-V4-Flash-2bit-DQ · 1 runs in the model record
answer: 17 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
  Max 128GB                          | 2-bit | 17 tok/s       | reported | ttft -ms | vram - GB | ctx 2,048