bestmodel.run / model — Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M (agent view)

category chat · JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M · 2 runs in the model record
answer: 188.9 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
  M5 Pro 24GB                        | 4-bit | 112.3 tok/s    | reported | ttft 283ms | vram - GB | ctx 4,224
  RTX 5070 12GB                      | 4-bit | 265.5 tok/s    | reported | ttft 67ms | vram - GB | ctx 2,048