Qwen 3-235B-A22B / Vulkan b10605 native PP512 TG128
on AMD Strix Halo 128GB · llama.cpp b10605 / a130532a / Vulkan
Summary
User reports Qwen3-235B-A22B at 21.8 t/s generation and 159.4 t/s prompt processing on a GMKtec EVO-X2 with Ryzen AI Max+ 395 and 128 GB unified memory.
Setup is llama-bench build b10605 on Vulkan with Q2_K, a 79.81 GB file, run entirely GPU-side on the integrated Radeon 8060S.
The figures are separate synthetic phases, PP 512 and TG 128, each a median of five runs with the highest and lowest dropped; no TTFT was measured.