Gemma 3 on mobile and web with Google AI Edge- Google Developers Blog
3/12/2025 · Marissa Ikonomidis, T.J. Alumbaugh, Mark Sherwood, Cormac Brick
What this post added
Introduces Gemma 3 1B, a new model size in the Gemma family, optimized for on-device deployment on mobile and web. Details the use of Google AI Edge's LLM inference API for efficient on-device processing, achieving up to 2585 tok/sec on prefill. Explains key performance optimizations including quantization-aware training (4-bit integer weights, dynamic int8 activation), optimized KV cache layouts, cached optimized weight layouts for faster loading, and GPU weight sharing for reduced memory footprint during prefill and decode phases. Provides guidance on deploying Gemma 3 1B on Android devices and in-browser, including performance metrics on specific hardware.