I was curious about how omni decision models could be used in rescue workers bodycams or smart glasses, so I decided to build a quick demo. …

I was curious about how omni decision models could be used in rescue workers bodycams or smart glasses, so I decided to build a quick demo. I went with @liquidai d1-omni-600M since it supports both vision and audio. The demo uses real footage with situation specific questions to generate structured decisions . It's still rough and has some hallucinations, but this feels like an interesting application for small decision models, especially given how lightweight they are and the potential to run them directly on bodycam and smart glasses. Media Today we release Open d1: two open-weight multimodal models in our d1 decision model family. > d1-3B: text + vision > d1-omni-600M: text + image or text + audio > Real-time decision making anywhere, from data centers such as @nvidia DGX to RTX workstations to Jetson at the edge. …

Source: Clem Delangue (X) | 2026-10-10