Google Gemma
Google's family of lightweight, open-weight AI models built from the same research as Gemini for on-device and local deployment.
Features
- Open-weight models from 2B to 27B parameters
- Optimized for on-device and edge deployment
- Built from Gemini research and training techniques
- Available on Hugging Face, Kaggle, and Google AI Studio
- Fine-tuning support with LoRA and QLoRA
Google Gemma is a family of lightweight, open-weight AI models built from the same research and technology as Google’s Gemini models. Available in sizes from 2B to 27B parameters, Gemma models are optimized for on-device deployment, local inference, and fine-tuning. They deliver strong performance relative to their size and are freely available for download from Hugging Face, Kaggle, and Google AI Studio.
Similar tools
Anthropic API
paidDeveloper platform and API for Claude models with long context, tool use, and enterprise features.
Anyscale
paidRay-based LLM platform for training, serving, and scaling AI workloads in the cloud.
AutoGen
open-sourceMicrosoft's open-source framework for building multi-agent AI systems with conversational patterns and tool use.