Gemma 4 31B
Gemma 4 31B Instruct is a dense multimodal model developed by Google DeepMind with 30.7 billion parameters. It supports both text and image inputs and provides text outputs, featuring a 256K token context window, configurable reasoning modes, native function calling, and multilingual support across 140+ languages. The model excels in coding, reasoning, and document understanding tasks.
What is Gemma 4 31B?
Gemma 4 31B is an AI model from Google that Agent Mag tracks for pricing, context window, modalities, benchmarks, and API compatibility. Builders can use this page to compare Gemma 4 31B against other models for agent workflows and production deployments.
Gemma 4 31B Instruct is a dense multimodal model developed by Google DeepMind with 30.7 billion parameters. It supports both text and image inputs and provides text outputs, featuring a 256K token context window, configurable reasoning modes, native function calling, and multilingual support across 140+ languages. The model excels in coding, reasoning, and document understanding tasks.