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.
With CoreAI, you can start chatting with Google: Gemma 4 31B instantly — no separate subscription needed. CoreAI bundles access to Google: Gemma 4 31B along with 300+ other AI models from Google and other providers like OpenAI, Anthropic, Google, Meta, and more.
Chat with Google: Gemma 4 31B and 300+ other AI models — all in one app.