Ollama model
gemma4
Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.
- Pulls
- 23.3M
- Tags
- 50
- Updated
- Aug 25, 2026
- Listed sizes
- e2b · e4b · 12b · 26b · 31b
Run locally
Copy one command. You stay in control.
The command downloads the default tag if needed, then starts it. Confirm the exact file size, license, context, and hardware requirement on the official page first.
ollama run gemma4- 1
Install Ollama on your Mac, Windows, or Linux computer.
- 2
Open Terminal and paste the copied command.
- 3
Press Enter to download the model if needed and start it.
Capabilities
What its library labels mean
- Vision
- Understands images and other supported visual input.
- Tools
- Can request compatible functions and external tools.
- Thinking
- Supports model reasoning controls through Ollama.
- Audio
- Accepts audio on supported model variants.
- Cloud
- Runs through Ollama's cloud rather than entirely on this computer.