DiggTop

Phi-4-mini-reasoning

Phi family · 4.0B params

1recorded run
108.2best tok/s
1verified
Fastest GPUs for this model (best tok/s)
  1. RTX 3060 x2108.2

All benchmarks Methodology

GPUModelQuantBackendCtx tok/sprompt tok/sVRAM GBSource
RTX 3060 x2 · 12 GBPhi-4-mini-reasoningQ4_K_Mllama.cpp 13f2b28512108.2 3875.28.6src