Benchmarked Gemma 4 31B ARA-heretic on GMKtec EVO-X2 (Ryzen AI Max+ 395 / Radeon 8060S) using llama.cpp ROCm. While short prompts hit 8.4 t/s, 62K context runs collapsed into <unused49> and leaked across slots. Here is how upgrading the build and configuring --cache-ram resolved it.
