llamaperf

Unknown family 27B

on NVIDIA RTX 5090 · NInfer

NVIDIA hardware
Oct 9, 2026
Throughput
130-200 t/s gen
Quant
NVFP4 (NVFP4)

Summary

User reports a ~27B NVFP4 model on an RTX 5090 running 130-200 tok/s when the terminal window is focused, dropping to 50-60 tok/s when unfocused. Setup is NInfer on Windows; the slowdown was traced to CPU-side scheduling (wait 16-17 ms focused vs 38-41 ms unfocused), not GPU throttling, since SM clocks were higher during slow runs (2550-2600 MHz vs 2100-2200 MHz) at the same 400 W power limit. Running the server detached or headless fixed it, keeping throughput around 130-200 tok/s regardless of window focus; the same behavior reproduced with a native Windows build, so it is not WSL2-specific.