Ollama model
embeddinggemma-2
EmbeddingGemma 2 is a multimodal embedding model from Google built on the Gemma 4 architecture.
- Pulls
- 75.8K
- Tags
- 21
- Updated
- Oct 15, 2026
- Listed sizes
- 270m · 440m · 570m · 740m
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 embeddinggemma-2- 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.
- Embedding
- Turns text into vectors for retrieval, search, and RAG.
- Audio
- Accepts audio on supported model variants.