About Gemma 4 31B
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.
Specifications
- Provider
- Context Length
- 262,144 tokens
- Input Types
- image, text, video
- Output Types
- text
- Category
- Gemini
- Added
- 4/2/2026