bestmodel.run / model — LFM2-350M-NVFP4A16 (agent view)

category chat · apolloparty/LFM2-350M-NVFP4A16 · 1 runs in the model record
answer: 11,076,834,495.3 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
  RTX 5090 32GB                      | 4-bit | 2,231.4 tok/s  | reported | ttft -ms | vram 28.4 GB | ctx 704