Qwen 3.5-9B / RADV native TG128 only
on AMD Strix Halo 128GB · llama.cpp / Vulkan RADV / build unknown
Summary
User reports Qwen3.5-9B at 22.5 t/s generation on a single Radeon 8060S gfx1151 in an AMD Ryzen AI MAX+ 395 with 128 GB unified memory.
Setup is native llama-bench with Q8_0 weights, full GPU offload, batch 2048, 32 threads and flash attention 1, measured on the RADV backend.
The figure is the tg128 phase, 128 generated tokens, not simultaneous prompt and generation throughput; the same model reached 23.3 t/s on AMDVLK and 22.3 t/s on ROCm.