Gemma 3
Lightweight open-weight LLM by Google available in 1B to 27B sizes.
About
Gemma 3 by Google DeepMind is an open-weight model family in 1B, 4B, 12B, and 27B sizes, built from Gemini research. It supports a 128K-token context, image input on the larger variants, function calling, and more than 35 languages, and runs on a single GPU. The repository provides a JAX package for using and fine-tuning the models with a chat sampler API. Released under the Gemma license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Large Language Models (LLMs)
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- Gemma License
- Minimum VRAM
- 4 GB
- Added
- Apr 3, 2026
Related Tools
Open-source code LLM family by IBM for enterprise code generation.
High-performance open-weight MoE LLM with 671B total parameters.
Hybrid SSM-Transformer model by AI21 Labs combining Mamba with attention layers.
State-space model for language with linear-time sequence modeling.
Family of small language models by Hugging Face for on-device use.
Open-weight LLM by Meta in 8B and 70B sizes with strong general capabilities.