unsloth/gemma-3-12b-it

The Gemma 3 12B IT model by Google DeepMind is a 12 billion parameter instruction-tuned multimodal language model with a 128K token context window. It handles both text and image inputs to generate text outputs, supporting over 140 languages. This model is optimized 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.