Gemma
- Price
- Free
- API
- Yes
- Weights
- Yes
WHAT IT DOES
Gemma is Google DeepMind's family of open-source large language models, serving as lightweight versions of Gemini. Available models include Gemma 1 (February 2024), Gemma 2 (June 2024), and Gemma 3 (March 2026) with variants like PaliGemma for vision-language tasks and MedGemma for medical applications. Available in multiple sizes (2B, 7B, and larger variants). Designed for research, education, and commercial applications with permissive licensing. Trained on similar data and methods as Gemini models but optimized for open-source deployment. Available through Hugging Face, Kaggle, and Google Cloud Vertex AI.
WHY WE PICKED IT
Google's open-source LLM family with strong performance, permissive licensing, and specialized variants for vision and medical applications.
QUICK FACTS
STRENGTHS
- ✓Open-source with permissive licensing
- ✓Multiple model sizes for different use cases
- ✓Specialized variants (PaliGemma, MedGemma)
- ✓Strong performance relative to model size
- ✓Backed by Google DeepMind research
LIMITATIONS
- ⚠Smaller than full Gemini models
- ⚠May have limitations on very complex tasks
- ⚠Requires technical expertise for local deployment
- ⚠Some features may lag behind proprietary Gemini
- ⚠Community support vs enterprise support
GETTING STARTED
Visit Google's Gemma documentation at ai.google.dev/gemma or deepmind.google/technologies/gemma. Download model weights from Hugging Face (huggingface.co/google) or Kaggle (kaggle.com/models/google/gemma). For API access, use Google Cloud Vertex AI. Deploy locally using PyTorch, JAX, or TensorFlow. Gemma 3 (March 2026) is the latest version with improved performance. Follow Google's documentation for setup, fine-tuning, and deployment. Free to use for research and commercial applications under permissive licensing.
QUICK TIPS
OFFICIAL LINKS
SIMILAR TOOLS
USE CASE EXAMPLES
Research and Education
Use Gemma for AI research, education, and academic projects with full access to model weights and training data.
- Download Gemma models from Hugging Face or Kaggle
- Set up research environment with PyTorch or JAX
- Conduct experiments and fine-tuning
- Publish research with full transparency
Vision-Language Applications
Use PaliGemma variant for tasks requiring both image and text understanding.
- Download PaliGemma model weights
- Set up vision-language pipeline
- Process images and text together
- Generate multimodal outputs
PRICING
FEATURED IN GUIDES
Open Models: What They Cannot Do
The benchmark gap has largely closed: open models now score within a point of the closed frontier on...
Hardware For Local AI Models: What The Memory Shortage Changed
Capacity decides whether a model runs. Bandwidth decides how fast it talks, and it is the number mos...
How To Run AI Models Locally: Hardware, Quantisation And Engines
Running a frontier open model locally is a memory problem before it is a speed problem, and a bandwi...
Uncensored AI Models: What Abliteration Actually Does To Them
Abliteration removes a model's ability to refuse by deleting one direction from its activations. It ...
Which LLMs Actually Deliver in 2026?
Comprehensive comparison of the best large language models in 2026 including ChatGPT, Claude, Gemini...
EXPLORE ALTERNATIVES
Compare Gemma with 5+ similar llms AI tools.
FREQUENTLY ASKED QUESTIONS
Is Gemma free?
Yes, Gemma is completely free to use.
Does Gemma have an API?
Yes, Gemma offers an API for programmatic integration.
What is Gemma best for?
Gemma is best for Research. Gemma is Google DeepMind's family of open-source large language models, serving as lightweight versions of Gemini. Google's open-source LLM family with strong performance, permissive licensing, and specialized variants for vision and medical applications.
What platforms does Gemma support?
Gemma supports api, local.
Is Gemma open source?
Yes, Gemma is open source. You can access the source code on GitHub at https://github.com/google/gemma_pytorch.
How do I get started with Gemma?
Visit Google's Gemma documentation at ai.google.dev/gemma or deepmind.google/technologies/gemma. Download model weights from Hugging Face (huggingface.co/google) or Kaggle (kaggle.com/models/google/gemma). For API access, use Google Cloud Vertex AI. Deploy locally using PyTorch, JAX, or TensorFlow. ...
How do I use Gemma?
Gemma is a large language model for text generation, analysis, and conversation. Use the API for programmatic access. Enter prompts or questions to get responses. It excels at open-source with permissive licensing.
FEATURED ON CURATEDAI
Work on Gemma? You're hand-reviewed in our directory. Add this badge to your site — it links back to this profile.
