Gemma 2

by Google · Website

Google's Gemma 2 is a family of lightweight, open-weight models built from the same research and technology used to create the Gemini models. Available in 2B, 9B, and 27B parameter sizes, Gemma 2 models deliver strong performance for their size class with a focus on responsible AI development and broad accessibility.

Variants (3)

Smallest: Gemma 2 2B (2B)
Largest: Gemma 2 27B (27B)

Gemma 2 2B

Google

2B
Min 2.7 GB
text-generation code-generation multilingual summarization

Gemma 2 9B

Google

9B
Min 6.9 GB
text-generation code-generation reasoning multilingual popular

Gemma 2 27B

Google

27B
Min 17.7 GB
text-generation code-generation reasoning multilingual