Models
June 27, 2025

Google launches Gemma 3n

Gemma 3n is a new open-weight model for on-device text, image, and audio processing. It integrates with tools like LMStudio, Ollama, and Hugging Face, enhancing privacy and autonomy

Google has released Gemma 3n, an open-weight multimodal model designed for on-device use. It handles text, image, and audio inputs, offering developers a privacy-focused AI solution without cloud dependency.

The model is compatible with popular tools including LMStudio, Ollama, and Hugging Face, making it easy to integrate across development stacks. By enabling multimodal processing on-device, Gemma 3n supports fast, secure, and autonomous applications for tasks like voice commands, image interpretation, and local reasoning.

This release underlines the growing trend toward decentralized AI and empowers innovators to embed advanced AI directly into apps and devices.

#
Google

Read Our Content

See All Blogs
AWS

New AWS enterprise generative AI tools: AgentCore, Nova Act, and Strands SDK

Deveshi Dabbawala

August 12, 2025
Read more
ML

The evolution of machine learning in 2025

Siddharth Menon

August 8, 2025
Read more