Qwen3.8 27B Swift

User reports Swift-Qwen3.8-27B at 24.6 t/s decode and 492 t/s prefill on a single Radeon PRO V620 32GB. Setup is a llama.cpp fork for gfx1030 with Q4_K_XL GGUF (16.6 GiB), flash attention, 128k context, card at 300 W. Decode falls to 16.9 t/s at 128k depth; with an MTP drafter it reaches 48.0 t/s at depth 0 and 44.1 t/s at 120k, while DFlash2 peaks at 76 t/s on short mixed work.