Qwen3 30B (3B active)
on AMD Radeon 8060S integrated GPU (Strix Halo; installed RAM unreported) · llama.cpp b5349 / 9a390c48 / Vulkan RADV
Summary
User reports Qwen3-30B-A3B at 69.3 t/s generation and 163.8 t/s prompt processing on an AMD Ryzen AI Max+ 395 / Radeon 8060S under Linux.
Setup is llama.cpp Vulkan with UD-Q4_K_XL, ngl 99, batch size 128 and flash attention enabled, on one local GPU.
The two figures are separate llama-bench phases, PP512 and TG128, not a same-request pair; context depth is unreported.