unsloth/gemma-3-4b-it

Gemma 3 4B IT is a 4.3 billion parameter multimodal model developed by Google DeepMind, built from the same research and technology as the Gemini models. It handles text and image inputs to generate text outputs, featuring a 128K context window and multilingual support across 140+ languages. This instruction-tuned variant is well-suited for diverse text generation and image understanding tasks, including question answering, summarization, and reasoning, while being deployable in resource-limited environments.