Google: Gemma 4 31B logo

Google: Gemma 4 31B

Googlellm

Published April 2, 2026

About

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.

Try Google: Gemma 4 31B

Test this model in the Sandbase Playground with your own prompts.

Open in Playground

Related Models