If you are running Qwen 3.8 Flash Next on Strix Halo, use this software for inference. It's so much faster than llama.cpp especially at high context.

Here's the project. I have nothing to do with it. I'm just an amazed user. https://github.com/gufo-org/gufo/blob/main/docs/models/qwen3.8-flash-next/BENCHMARKS.md Those benchmark numbers hold up on real work loads. Here are some numbers I got during a chat. "[6204 chunks in 119.0 s | encode: 1239 to