Qwen3.8 27B
on AMD Ryzen AI Max+ 395 / Radeon 8060S (Strix Halo; memory capacity unreported) · llama.cpp
Summary
User reports Qwen3.8-27B UD-IQ3_XXS at 18.3 t/s generation and 313.3 t/s prompt processing on a single Ryzen AI Max+ 395 / Radeon 8060S.
Setup is llama.cpp with llama-bench over Vulkan; the RTX 3060 in the same host is excluded from this control.
The 313.3 t/s is a pp4096 test and the 18.3 t/s a tg64 test, independent synthetic runs rather than a paired 4096-input/64-output request. A pp65536 test reached 136.69 t/s, and a pp98304 test timed out after 900 seconds.