Qwen3.5 4B
on AMD Radeon 8060S integrated GPU (Strix Halo, gfx1151) · 1bit engine / llama.cpp (Vulkan 7fe450e)
Summary
User reports Qwen3.5 4B at 60 t/s generation and 1992 t/s prompt processing on one Strix Halo integrated GPU.
Setup is llama.cpp Vulkan with UD-Q4_K_XL, run as native llama-bench pp512 and tg128 phases.
The figures are separate synthetic prompt-processing and token-generation phases, not a 512-token prompt followed by a 128-token chat, and total context capacity is unspecified.