google/gemma-3-27b-pt

Gemma 3 is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. The google/gemma-3-27b-pt model is a 27 billion parameter pre-trained variant, offering multimodal capabilities for text and image input with text output. It features a large 128K context window and multilingual support in over 140 languages. This model is well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning, and is designed for deployment in resource-limited environments.