Qwen3.8 125B (6B active) Flash-Next
on AMD Strix Halo 128GB · llama.cpp
Summary
User reports Qwen3.8 Flash Next reaching 1.2k t/s prefill on Strix Halo 128GB.
Setup is a custom llama.cpp branch with a custom HIP runtime, built to match the closed-source Halogen server's prefill numbers; the community fork had only reached 400 t/s.
The user plans to clean up the work and submit PRs to mainline and the community fork, noting the approach may also help the GLM 5.3 Flash architecture.