Qwen3.8 125B (6B active) Flash-Next
on 2× CMP 170HX
Summary
User reports prompt processing around 4000 t/s and decode above 80 t/s on a single stream on a DIY CUDA box with two CMP 170HX cards.
Setup runs Qwen Flash Next, with Qwen 27B and Gemma 26B also mentioned.