Gemma 4 Huihui E4B-it-abliterated, LiteRT-LM GPU benchmark

User reports Gemma 4 at 16.5 t/s generation and 518.3 t/s prompt processing on an M4 with 16 GB unified memory. Setup is LiteRT-LM on the GPU backend with dynamic_wi8_afp32 quantization and a 4,096-token maximum context, using a 256-token prefill and 256-token decode benchmark. The source gives exact rates of 16.53 t/s decode and 518.28 t/s prefill, and does not establish whether the phases were separate tests or one request.