Qwen3.8 Flash-Next / W4B HGN quality overlay / idle resident peer / code r1
on AMD Strix Halo 128GB · Halogen 0.9.1 HIP / quality overlay / co-resident peer idle · 262,144 ctx
Summary
User reports Qwen3.8 at 49.5 t/s generation and 358.5 t/s prompt processing on an AMD Strix Halo 128GB machine.
Setup is Halogen 0.9.1 with a W4B HGN quant plus quality overlay, 262144 context per request, MTP and prompt lookup enabled, on one Ryzen AI MAX+ 395 APU with 128 GB unified memory.
The 49.5 t/s and 358.5 t/s come from a single idle-peer fixed-code repeat with 524 input and 256 output tokens; the same run's client-side generation was 50.974291±1.201111 t/s.