zoom_in Click to enlarge

Gemma 2

▲ ▼

language

description Gemma 2 Overview

Gemma 2 is Google's second generation family of open-weight language models, introduced in 2024. It was released in 2-billion, 9-billion, and 27-billion parameter versions, allowing developers and researchers to choose among different memory and computing requirements for local or hosted deployment. The family is designed for text generation and related language tasks, with weights available under Google's Gemma terms rather than a conventional open-source software license.

help Gemma 2 FAQ

Is Gemma 2 an open-source language model?

Gemma 2 is released as an open-weight model family, meaning Google provides the model weights to the public for local deployment and research. This allows developers to modify and run the models offline, subject to Google's acceptable use policy.

Who created the Gemma 2 models?

The Gemma 2 family of large language models was developed and released by Google in 2024. It represents Google's second generation of lightweight, open models derived from the research and technology used for their larger Gemini models.

Can Gemma 2 be run locally on consumer hardware?

Yes, the smaller 2-billion and 9-billion parameter versions of Gemma 2 are specifically designed to be run efficiently on consumer-grade hardware. Developers frequently use quantization techniques alongside local inference engines to run these models on standard laptops.

swap_horiz

Looking for Gemma 2 alternatives? Compare top competitors ranked & scored

arrow_forward