unsloth/gemma-3-12b-pt

Gemma 3 (12B) is a 12 billion parameter multimodal language model from Google, built on the same research as Gemini models. It handles both text and image inputs, generating text outputs, and features a large 128K token context window with multilingual support across 140+ languages. This model is optimized for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning, and is suitable for deployment in resource-limited environments.