Shisa V2 Llama 3.3 70B i1-Q4_K_M / Vulkan b5349 / native PP512 and separate TG128

User reports Shisa V2 Llama 3.3 at 5 t/s generation and 77.3 t/s prompt processing on a Ryzen AI Max+ 395 / Radeon 8060S under Linux. Setup is llama.cpp Vulkan with the i1-Q4_K_M quant, full offload (ngl 99) and flash attention, on one local GPU. The figures are separate llama-bench phases: PP512 at 77.28 +/- 0.69 t/s and TG128 at 5.02 +/- 0.00 t/s, not a same-request pair. Context depth and batch size are unreported.