Qwen3.8 125B (6B active) Flash-Next
on 3× AMD MI50 32GB · llama.cpp · 130,000 ctx
Sep 9, 2026
Summary
User reports 15 t/s generation and 100-200 t/s prompt processing at 130k context.
Setup is ROCm with flash-attn, split-mode layer and fit on.
The user notes Vulkan gives similar speed.