Qwen 3.5-35B-A3B / AesSedai Q4_K_M / RADV native PP512 only
on AMD Strix Halo 128GB · llama.cpp / Vulkan RADV / build unknown
Summary
User reports Qwen3.5-35B-A3B at 832 t/s prompt processing on a single Radeon 8060S gfx1151 in an AMD Ryzen AI MAX+ 395 with 128 GB unified memory.
Setup is native llama-bench with AesSedai Q4_K_M, full GPU offload, batch 2048, 32 threads and flash attention 1; the 21 GiB artifact is disk size, not measured GPU memory.
The 832 t/s is the RADV pp512 phase; the AMDVLK tg128 phase reached 53 t/s, and PP and TG are separate phases rather than simultaneous throughput.