granite3.2-vision

Granite3.2-vision is an AI model by IBM that processes both text and images, supporting multimodal tasks like visual question answering, with integration into frameworks such as Llama 3.2 Vision for enhanced vision-language capabilities.

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.