Qwen3.8 27B
on AMD Strix Halo 128GB · llama.cpp / ROCm (build unreported)
Summary
User reports Qwen3.8-27B at 12.1 t/s generation and 378.2 t/s prompt processing on an AMD Strix Halo 128GB machine.
Setup is llama-bench on the ROCm backend with the UD-Q4_K_XL GGUF, no speculative decoding, no chat template and no client, at depth 0.
The run is a depth sweep: generation falls from 12.06 t/s at depth 0 to 9.05 t/s at depth 100000, and prompt processing from 378.24 t/s to 121.85 t/s. Each PP and TG entry is a separate phase, not one request.