Gemma 4 5.1B E2B

User reports Gemma 4 E2B at 15.3 t/s generation and 28.5 t/s prefill on an Xbox Series S, CPU-only with six inference threads. Setup is llama.cpp in xllama 1.6.0.1163 with Q3_K_S and a configured context of 2048, one sequential text request per fresh app process. The figures are separate medians of three recorded runs, with generation ranging 15.27–15.31 t/s; peak working set was 2741 MB per run.