Llama 4 Scout 17B-16E / Q4_K_XL / Vulkan native PP512 TG128 / runtime build unknown
on AMD Strix Halo 128GB · llama.cpp / Vulkan KHR cooperative matrices / build unknown
Summary
User reports Llama 4 Scout 17B-16E at 20.2 t/s generation and 225 t/s prompt processing on an AMD Strix Halo 128GB machine.
Setup is llama.cpp Vulkan on the Radeon 8060S iGPU with Q4_K_XL, 6 threads and maximum GPU offload.
The figures come from separate llama-bench phase tests, a 512-token prompt and 128-token generation, not an end-to-end rate; rates are rounded and context depth, KV precision and batch settings are unreported.