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 PlaygroundRelated Models
Google: Gemini 2.0 Flash LiteGooglellmGoogle: Gemini 2.5 FlashGooglellmGoogle: Nano Banana (Gemini 2.5 Flash Image)GooglellmGoogle: Gemini 2.5 Flash LiteGooglellmGoogle: Gemini 2.5 Flash Lite Preview 09-2025GooglellmGoogle: Gemini 2.5 ProGooglellmGoogle: Gemini 2.5 Pro Preview 06-05GooglellmGoogle: Gemini 2.5 Pro Preview 05-06Googlellm