bestmodel.run / model — Muse-Glimmer-30B-NVFP4 (agent view)

category chat · Preyazz/Muse-Glimmer-30B-NVFP4 · 3 runs in the model record
answer: 124.8 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
  RTX 5090 32GB                      | 4-bit | 94.1 tok/s     | reported | ttft 31ms | vram - GB | ctx 8,192
  RTX PRO 6000 Blackwell 96GB        | 4-bit | 152.2 tok/s    | reported | ttft 22ms | vram - GB | ctx 32,768