Model•active
Gemma 4 12B
Gemma 4 12B is an 11.95B-parameter open-weight dense multimodal model from Google DeepMind for reasoning, coding and local multimodal workloads.
Official siteVerified Oct 4, 2026
Overview
The 12B Unified model supports text, image and native audio input, a 256K context window, multilingual use and local deployment on laptop-class hardware.
Model specifications
- Family
- Gemma 4
- Context
- 256,000 tokens
- Input
- Text, Image, Audio
- Output
- Text
- Open weights
- Yes
- Capabilities
- Reasoning, Vision, Tool Use, Function Calling