Cosmos3-Edge β Hexagon NPU (Understanding)
Prebuilt Qualcomm Hexagon NPU artifacts for the understanding half of nvidia/Cosmos3-Edge β a vision-language model that runs on-device. It reads and answers: given text (and optionally an image), it produces text.
Capabilities
- Text chat β an instruction-following language model for conversation, question answering, and reasoning. Text in β text out.
- Image understanding β a vision-language model for visual question answering and captioning. Image + text in β text out.
Both capabilities are served by one shared language backbone, so a single install handles chat and vision.
Family β Cosmos3-Edge is shipped as two arch-pinned edge bundles by task:
- this repo β understanding (chat + vision), text output
- Cosmos3-Edge β Image β generation, image output
Artifacts are arch-pinned; this repo currently contains the v81/ directory.
For model architecture, intended use, limitations, and license terms, see the upstream model card: nvidia/Cosmos3-Edge. Distributed under the NVIDIA Open Model License inherited from the base model.
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support
Model tree for runanywhere/cosmos3_edge_HNPU
Base model
nvidia/Cosmos3-Edge