DEVOPSdigest

Google's Gemma 3n is the latest member of Google's family of open models. Google is announcing that Gemma 3n is now fully available for developers with the full feature set including supporting image, audio, video and text.

Gemma 3n is the latest in the popular Gemma family of open models, but built on a new architecture specifically for high-performance AI on phones, tablets, and laptops.

Gemma 3n is designed for the developer community that helped shape Gemma. It’s supported by your favorite tools including Hugging Face Transformers, llama.cpp, Google AI Edge, Ollama, MLX, and many others, enabling you to fine-tune and deploy for your specific on-device applications with ease. This post is the developer deep dive: we'll explore some of the innovations behind Gemma 3n, share new benchmark results, and show you how to start building today.

Key Features: Gemma 3n brings powerful, multimodal AI (supporting image, audio, video, and text inputs), enabling real-time, offline-capable AI directly on-device.

Performance Milestone: Its E4B version is the first model under 10B parameters to score over 1300 on the LMArena benchmark, achieving performance previously seen in large, cloud-based models.

Dev Competition: Google is launching a $150,000 Gemma 3n Impact Challenge competition on Kaggle for developers to use Gemma 3n's unique on-device, offline, and multimodal capabilities to build apps for social good (i.e. accessibility, education, healthcare, sustainability, crisis response).