Qualcomm® AI HubAI Hub

Segment-Anything-Model-3

Open‑vocabulary segmentation with text and visual prompts for any concept.

SAM3 (Segment Anything with Concepts) extends SAM2 with open‑vocabulary segmentation, producing bounding boxes and masks for objects matching a natural‑language prompt.

Note: Segment-Anything-Model-3 cannot be downloaded directly due to licensing restrictions. You can export a model ready for on-device deployment using the AI Hub service.

Export with Workbench
Not supported

This model is currently not supported on any Automotive chipset.

To see performance metrics for this model on other chipsets, click the button below.

View for other chipsets
Model RepositoryHugging FaceResearch Paper

Technical Details

Input resolution:1008x1008
Model checkpoint:sam3
Model size (SAM3Backbone) (float):128 MB
Model size (SAM3Transformer) (float):23.7 MB
Number of parameters (SAM3Backbone):33.5M
Number of parameters (SAM3Transformer):6.22M

Applicable Scenarios

  • Factory Automation
  • Robotic Navigation
  • Camera

License

Model:SAM3

Tags

  • foundation

Supported Automotive Devices

  • SA7255P ADP
  • SA8255P ADP
  • SA8295P ADP
  • SA8650P ADP
  • SA8775P ADP

Supported Automotive Chipsets

  • Qualcomm® SA7255P
  • Qualcomm® SA8255P
  • Qualcomm® SA8295P
  • Qualcomm® SA8650P
  • Qualcomm® SA8775P

Related Models

See all models
View details for the Segment-Anything-Model-2 model.

Segment-Anything-Model-2

High-quality segmentation in images and videos with real-time performance and minimal user interaction.

Sample Appsfeaturing Segment-Anything-Model-3

See all sample apps
View details for the SAM3 Segmentation Windows app.

SAM3 Segmentation Windows

Text-prompted on-device segmentation with SAM3

Looking for more? See models created by industry leaders.

Discover Model Makers