Qwen3.8 27B
on 2× AMD Radeon AI PRO R9700 32GB · vLLM · 94,065 ctx
Sep 7, 2026
Summary
User reports Qwen3.8 27B at 280 t/s decode on dual R9700s.
Setup is MXFP4 quantization. Prompt processing at 128k context runs at 3831 t/s.
The user notes the performance came from collaboration.