unsloth/gemma-3-1b-pt

unsloth/gemma-3-1b-pt is a 1 billion parameter pre-trained multimodal language model from Google DeepMind, part of the Gemma 3 family. It handles both text and image inputs, generating text outputs, and features a 32K token context window. This model is optimized for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning, and supports over 140 languages.