Gemma
Published Updated
What is Gemma?
A family of lightweight, open-weight models built by Google using the same research and technology used to create the flagship Gemini models.
Gemma models are the open-weight counterparts to Google's proprietary Gemini APIs. They are optimized for developer accessibility, fitting easily onto standard developer laptops while maintaining high safety standards and strong integration with Google Cloud's deployment tools.
How it relates to Orbit
Gemma can run under Ollama or LM Studio, and Orbit can route a complexity tier to either. See Complexity Tiers & Routing for details.
When you would use it
You use Gemma when you want a Google-engineered open-weight model that integrates directly into the Keras, PyTorch, and Google Cloud ecosystems.
Common operations
- Fine-tuning lightweight models in Google Colab.
- Deploying cost-effective, self-hosted text processing pipelines.
Related terms
Where this is taught
No learning path uses this term yet. Browse the Learning Atlas for guided sequences through related ideas.