Qwen3.6 27B-OBLITERATED-MTP / Vulkan native PP2048 TG128, MTP off

User reports Qwen3.6 at 13.7 t/s generation and 295 t/s prompt processing on an AMD Strix Halo 128GB machine. Setup is the charlie12345/rocmfp4-llama fork with ROCmFP4 STRIX hybrid quantization, F16 embeddings and a Q6_K output head, run through native llama-bench with -ngl 999 -fa 1 -ub 1024 -r 3 and no MTP. The 13.7 t/s is the Vulkan0 TG128 figure and 295 t/s the Vulkan0 PP2048 figure, separate synthetic tests rather than one request; a ROCm0 arm measured 13.5 t/s and 335 t/s. Native batch size, KV types, context capacity and resident memory are unpublished.