Gemma

Gemma is a family of lightweight, state-of-the-art https://opensource.googleblog.com/2024/02/building-open-models-responsibly-gemini-era.html built from the same research and technology used to create the Gemini models.

Gemma is Google’s latest family of lightweight, state-of-the-art open-source language models, built using the same advanced research and technology behind the Gemini models. Designed for versatility, Gemma 3 excels in handling complex tasks with its 128K-token context window, enabling applications to process vast amounts of data for sophisticated AI capabilities. It supports over 140 languages, making it ideal for global communication, and can analyze text, images, and video for intelligent, interactive applications. Gemma is optimized for deployment across mobile, web, and cloud platforms, offering low-latency, scalable, and privacy-focused solutions. Additionally, it provides specialized models for advanced research, supported by Google Cloud credits, empowering developers and researchers to innovate and push the boundaries of AI.