Qwen3.8 27B
on AMD Gorgon Halo 192GB · llama.cpp
Oct 11, 2026
Summary
User reports Qwen3.8 27B at 8.1 t/s generation and 466 t/s prompt processing on an AMD Gorgon Halo 192GB machine.
Setup is llama.cpp with Q8_0 and all layers on the GPU, on a Minisforum MS-S1 MAX-P495 with Ryzen AI Max+ PRO 495 and 192 GB unified memory.
The 466 t/s and 8.1 t/s come from separate llama-bench pp512 and tg128 tests, not a paired 512-input/128-output run; the same source separately reports about 100 t/s prompt and 7.5 t/s generation at roughly 32k depth.