Qwen3.8 125B (6B active) Flash-Next
on 2× NVIDIA RTX 5090 · llama.cpp
Sep 18, 2026
Summary
User reports Qwen3.8 Flash-Next at 90-100 t/s decode and 3000 t/s prefill on two RTX 5090s across two machines.
Setup is llama.cpp with RPC over a ConnectX-5 100G link, using Unsloth Q2 quants.
User sees little practical reason to use this over the 27B model and asks what others get with 2x 5090 in one machine or a 6000 Pro.