llamaperf

Qwen3.8 125B (6B active) Flash-Next

on DGX Station - ASUS Pro ET900N G3

Tone: mixed
Oct 12, 2026
Throughput
200.0 t/s gen
Quant
NVFP4 (NVFP4)

Summary

User reports Qwen3.8-Flash-Next at 200 tokens/second on a DGX Station (ASUS Pro ET900N G3). No engine, context length or KV cache settings are stated; the run is described as untuned so far. The user notes the machine's electricity consumption as a caveat.