A compact multimodal model that handles both text and image inputs, producing text outputs. At 4B parameters, it sits in the lightweight tier — capable of visual understanding tasks without the resource demands of larger models, though its smaller size means it may handle complex reasoning less robustly than bigger counterparts. It's a base model, meaning it hasn't been fine-tuned for chat or instruction-following, so it behaves more like a raw foundation than a polished assistant.