MedGemma 1.5

MedGemma 1.5, developed by Google DeepMind, is a 4-billion-parameter open-source multimodal model specialized for medical tasks like 3D imaging and document analysis, designed to run efficiently on a single consumer GPU.

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.