mobile AI

PrismML has released Bonsai 27B, claiming it's the first 27-billion parameter model capable of running on-device on iPhone. The model achieves 58-87 tokens per second on Apple's M5 Max chip with a 4GB memory footprint, using 1-bit and ternary quantization to fit within iPhone's approximately 6GB available app memory.

Google is rolling out Gemini Go, a streamlined version of its Gemini AI assistant designed for Android Go devices with 2GB of RAM or more. The update replaces Assistant Go and integrates into the Google Search app on entry-level Android phones.

Google is expanding Search Live globally to users in more than 200 countries, enabling real-time voice and camera search through the Google app and Lens. The feature, powered by Gemini 3.1 Flash Live—a new multilingual audio and video model—allows users to point their phone camera at objects and ask questions with instant spoken responses.