Hugging Face's logo

qualcomm
/
MobileSam

Image Segmentation
PyTorch
foundation
android
Model card Files
xet
 Community

MobileSam: Optimized for Qualcomm Devices

Transformer based encoder-decoder where prompts specify what to segment in an image thereby allowing segmentation without the need for additional training. The image encoder generates embeddings and the lightweight decoder operates on the embeddings for point and mask based image segmentation.

This is based on the implementation of MobileSam found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime Precision Chipset SDK Versions Download
ONNX float Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit MobileSam on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

  • Custom weights (e.g., fine-tuned checkpoints)
  • Custom input shapes
  • Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for MobileSam on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

  • Input resolution: 720p (720x1280)
  • Model checkpoint: vit_t
  • Model size (sam_decoder) (float): 23.7 MB
  • Model size (sam_encoder) (float): 26.6 MB
  • Number of parameters (sam_decoder): 6.16M
  • Number of parameters (sam_encoder): 6.95M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
decoder ONNX float Snapdragon® X2 Elite 2.631 ms 4 - 4 MB NPU
decoder ONNX float Snapdragon® X Elite 6.205 ms 11 - 11 MB NPU
decoder ONNX float Snapdragon® 8 Gen 3 Mobile 4.046 ms 0 - 270 MB NPU
decoder ONNX float Snapdragon® 8 Gen 1 Mobile 14.679 ms 5 - 235 MB NPU
decoder ONNX float Qualcomm® Dragonwing™ IQ-8275 6.285 ms 4 - 8 MB NPU
decoder ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.902 ms 4 - 149 MB NPU
decoder ONNX float Qualcomm® QCS8450 14.679 ms 5 - 235 MB NPU
decoder ONNX float Qualcomm® Dragonwing™ IQ-9075 6.896 ms 4 - 7 MB NPU
decoder ONNX float Qualcomm® Dragonwing™ IQ-X7181 6.205 ms 11 - 11 MB NPU
decoder ONNX float Qualcomm® Dragonwing™ Q-8750 3.2 ms 2 - 236 MB NPU
decoder ONNX float Snapdragon® 8 Elite Mobile 3.2 ms 2 - 236 MB NPU
decoder ONNX float Snapdragon® 8 Elite Gen 5 Mobile 2.536 ms 4 - 217 MB NPU
decoder QNN_DLC float Snapdragon® X2 Elite 2.929 ms 4 - 4 MB NPU
decoder QNN_DLC float Snapdragon® X Elite 5.933 ms 4 - 4 MB NPU
decoder QNN_DLC float Snapdragon® 8 Gen 3 Mobile 3.768 ms 4 - 221 MB NPU
decoder QNN_DLC float Snapdragon® 8 Gen 1 Mobile 11.738 ms 0 - 220 MB NPU
decoder QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 5.763 ms 4 - 11 MB NPU
decoder QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 12.753 ms 1 - 193 MB NPU
decoder QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.462 ms 4 - 6 MB NPU
decoder QNN_DLC float Qualcomm® SA8775P 6.377 ms 0 - 193 MB NPU
decoder QNN_DLC float Qualcomm® SA8650P 6.377 ms 0 - 193 MB NPU
decoder QNN_DLC float Qualcomm® SA8255P 6.377 ms 0 - 193 MB NPU
decoder QNN_DLC float Qualcomm® QCS8450 11.738 ms 0 - 220 MB NPU
decoder QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 6.208 ms 4 - 10 MB NPU
decoder QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 5.933 ms 4 - 4 MB NPU
decoder QNN_DLC float Qualcomm® Dragonwing™ Q-8750 2.859 ms 4 - 226 MB NPU
decoder QNN_DLC float Qualcomm® SA7255P 12.753 ms 1 - 193 MB NPU
decoder QNN_DLC float Qualcomm® SA8295P 7.824 ms 0 - 195 MB NPU
decoder QNN_DLC float Snapdragon® 8 Elite Mobile 2.859 ms 4 - 226 MB NPU
decoder QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 2.57 ms 4 - 193 MB NPU
decoder TFLITE float Snapdragon® 8 Gen 3 Mobile 3.456 ms 0 - 211 MB NPU
decoder TFLITE float Snapdragon® 8 Gen 1 Mobile 8.327 ms 0 - 213 MB NPU
decoder TFLITE float Qualcomm® Dragonwing™ IQ-8275 5.35 ms 0 - 19 MB NPU
decoder TFLITE float Qualcomm® Dragonwing™ IQ-8275 11.819 ms 0 - 185 MB NPU
decoder TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.993 ms 0 - 13 MB NPU
decoder TFLITE float Qualcomm® SA8775P 5.865 ms 0 - 186 MB NPU
decoder TFLITE float Qualcomm® SA8650P 5.865 ms 0 - 186 MB NPU
decoder TFLITE float Qualcomm® SA8255P 5.865 ms 0 - 186 MB NPU
decoder TFLITE float Qualcomm® QCS8450 8.327 ms 0 - 213 MB NPU
decoder TFLITE float Qualcomm® Dragonwing™ IQ-9075 5.694 ms 0 - 19 MB NPU
decoder TFLITE float Qualcomm® Dragonwing™ Q-8750 2.612 ms 0 - 184 MB NPU
decoder TFLITE float Qualcomm® SA7255P 11.819 ms 0 - 185 MB NPU
decoder TFLITE float Snapdragon® 8 Elite Mobile 2.612 ms 0 - 184 MB NPU
decoder TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 2.197 ms 0 - 184 MB NPU
encoder ONNX float Snapdragon® X2 Elite 58.844 ms 12 - 12 MB NPU
encoder ONNX float Snapdragon® X Elite 116.8 ms 13 - 13 MB NPU
encoder ONNX float Snapdragon® 8 Gen 3 Mobile 82.792 ms 61 - 1181 MB NPU
encoder ONNX float Snapdragon® 8 Gen 1 Mobile 328.543 ms 20 - 1188 MB NPU
encoder ONNX float Qualcomm® Dragonwing™ IQ-8275 111.548 ms 12 - 16 MB NPU
encoder ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 117.242 ms 12 - 30 MB NPU
encoder ONNX float Qualcomm® QCS8450 328.543 ms 20 - 1188 MB NPU
encoder ONNX float Qualcomm® Dragonwing™ IQ-9075 121.741 ms 12 - 15 MB NPU
encoder ONNX float Qualcomm® Dragonwing™ IQ-X7181 116.8 ms 13 - 13 MB NPU
encoder ONNX float Qualcomm® Dragonwing™ Q-8750 62.301 ms 9 - 929 MB NPU
encoder ONNX float Snapdragon® 8 Elite Mobile 62.301 ms 9 - 929 MB NPU
encoder ONNX float Snapdragon® 8 Elite Gen 5 Mobile 52.463 ms 8 - 1027 MB NPU
encoder QNN_DLC float Snapdragon® X2 Elite 45.903 ms 12 - 12 MB NPU
encoder QNN_DLC float Snapdragon® X Elite 102.849 ms 12 - 12 MB NPU
encoder QNN_DLC float Snapdragon® 8 Gen 3 Mobile 66.12 ms 0 - 1315 MB NPU
encoder QNN_DLC float Snapdragon® 8 Gen 1 Mobile 328.88 ms 12 - 1342 MB NPU
encoder QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 91.963 ms 12 - 30 MB NPU
encoder QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 207.594 ms 1 - 1126 MB NPU
encoder QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 100.663 ms 12 - 15 MB NPU
encoder QNN_DLC float Qualcomm® SA8775P 100.335 ms 0 - 1549 MB NPU
encoder QNN_DLC float Qualcomm® SA8650P 100.335 ms 0 - 1549 MB NPU
encoder QNN_DLC float Qualcomm® SA8255P 100.335 ms 0 - 1549 MB NPU
encoder QNN_DLC float Qualcomm® QCS8450 328.88 ms 12 - 1342 MB NPU
encoder QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 101.207 ms 14 - 32 MB NPU
encoder QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 102.849 ms 12 - 12 MB NPU
encoder QNN_DLC float Qualcomm® Dragonwing™ Q-8750 49.202 ms 10 - 1125 MB NPU
encoder QNN_DLC float Qualcomm® SA7255P 207.594 ms 1 - 1126 MB NPU
encoder QNN_DLC float Qualcomm® SA8295P 324.884 ms 0 - 1556 MB NPU
encoder QNN_DLC float Snapdragon® 8 Elite Mobile 49.202 ms 10 - 1125 MB NPU
encoder QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 40.35 ms 11 - 1258 MB NPU
encoder TFLITE float Snapdragon® 8 Gen 3 Mobile 66.668 ms 3 - 3193 MB NPU
encoder TFLITE float Snapdragon® 8 Gen 1 Mobile 310.589 ms 4 - 1362 MB NPU
encoder TFLITE float Qualcomm® Dragonwing™ IQ-8275 86.395 ms 0 - 47 MB NPU
encoder TFLITE float Qualcomm® Dragonwing™ IQ-8275 196.915 ms 4 - 1633 MB NPU
encoder TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 90.801 ms 4 - 8 MB NPU
encoder TFLITE float Qualcomm® SA8775P 100.654 ms 0 - 1666 MB NPU
encoder TFLITE float Qualcomm® SA8650P 100.654 ms 0 - 1666 MB NPU
encoder TFLITE float Qualcomm® SA8255P 100.654 ms 0 - 1666 MB NPU
encoder TFLITE float Qualcomm® QCS8450 310.589 ms 4 - 1362 MB NPU
encoder TFLITE float Qualcomm® Dragonwing™ IQ-9075 101.13 ms 0 - 45 MB NPU
encoder TFLITE float Qualcomm® Dragonwing™ Q-8750 47.785 ms 2 - 1631 MB NPU
encoder TFLITE float Qualcomm® SA7255P 196.915 ms 4 - 1633 MB NPU
encoder TFLITE float Snapdragon® 8 Elite Mobile 47.785 ms 2 - 1631 MB NPU
encoder TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 39.872 ms 3 - 1795 MB NPU

License

  • The license for the original implementation of MobileSam can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Image Segmentation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for qualcomm/MobileSam

Quantizations
1 model

Paper for qualcomm/MobileSam