google/gemma-3-4b-it

Gemma 3 is a family of lightweight, state-of-the-art open models from Google DeepMind, built from the same research and technology used to create the Gemini models. This 4.3 billion parameter instruction-tuned variant is multimodal, handling text and image input to generate text output, and supports a large 128K context window. It excels at a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning, with multilingual support in over 140 languages. Its relatively small size allows for deployment in resource-limited environments like laptops and desktops.