EdgeTAM: Optimized for Qualcomm Devices

EdgeTAM is a lightweight and efficient version of SAM 2, optimized for on-device tracking and segmenting any object in videos and low memory usage by using a novel 2D Spatial Perceiver and RepViT backbone.

This is based on the implementation of EdgeTAM 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 2.42, ONNX Runtime 1.24.3 Download
ONNX w8a8 Universal QAIRT 2.42, ONNX Runtime 1.24.3 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a8 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download
TFLITE w8a8 Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit EdgeTAM 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 EdgeTAM on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

  • Model checkpoint: edgetam.pt
  • Input resolution (Encoder): 1024x1024
  • Number of parameters (encoder): 8.3M
  • Model size (encoder) (float): 33 MB
  • Number of parameters (decoder): 6.22M
  • Model size (decoder) (float): 23.7 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
decoder ONNX float Snapdragon® 8 Elite Gen 5 Mobile 3.154 ms 17 - 244 MB NPU
decoder ONNX float Snapdragon® 8 Elite Mobile 3.501 ms 2 - 241 MB NPU
decoder ONNX float Snapdragon® X2 Elite 3.277 ms 15 - 15 MB NPU
decoder ONNX float Snapdragon® X Elite 6.885 ms 16 - 16 MB NPU
decoder ONNX float Snapdragon® X Elite 6.885 ms 16 - 16 MB NPU
decoder ONNX float Snapdragon® 8 Gen 3 Mobile 4.729 ms 16 - 341 MB NPU
decoder ONNX float Qualcomm® QCS8550 (Proxy) 6.748 ms 16 - 24 MB NPU
decoder ONNX float Snapdragon® 8 Elite For Galaxy Mobile 3.501 ms 2 - 241 MB NPU
decoder ONNX float Qualcomm® QCS9075 8.43 ms 16 - 19 MB NPU
decoder ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 5.33 ms 4 - 272 MB NPU
decoder ONNX w8a8 Snapdragon® 8 Elite Mobile 6.739 ms 2 - 246 MB NPU
decoder ONNX w8a8 Snapdragon® X2 Elite 5.382 ms 4 - 4 MB NPU
decoder ONNX w8a8 Snapdragon® X Elite 12.523 ms 4 - 4 MB NPU
decoder ONNX w8a8 Snapdragon® X Elite 12.523 ms 4 - 4 MB NPU
decoder ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 9.191 ms 4 - 277 MB NPU
decoder ONNX w8a8 Qualcomm® QCS6490 136.586 ms 39 - 65 MB CPU
decoder ONNX w8a8 Qualcomm® QCS8550 (Proxy) 12.041 ms 2 - 10 MB NPU
decoder ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 51.069 ms 44 - 62 MB CPU
decoder ONNX w8a8 Qualcomm® QCM6690 58.52 ms 44 - 68 MB CPU
decoder ONNX w8a8 Qualcomm® QCS9075 14.799 ms 4 - 7 MB NPU
decoder ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 6.739 ms 2 - 246 MB NPU
decoder ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 51.069 ms 44 - 62 MB CPU
decoder QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 2.598 ms 16 - 202 MB NPU
decoder QNN_DLC float Snapdragon® 8 Elite Mobile 2.873 ms 4 - 187 MB NPU
decoder QNN_DLC float Snapdragon® X2 Elite 3.028 ms 16 - 16 MB NPU
decoder QNN_DLC float Snapdragon® X Elite 5.493 ms 16 - 16 MB NPU
decoder QNN_DLC float Snapdragon® X Elite 5.493 ms 16 - 16 MB NPU
decoder QNN_DLC float Snapdragon® 8 Gen 3 Mobile 3.644 ms 3 - 214 MB NPU
decoder QNN_DLC float Qualcomm® QCS8550 (Proxy) 5.391 ms 16 - 18 MB NPU
decoder QNN_DLC float Qualcomm® SA8775P 6.507 ms 16 - 224 MB NPU
decoder QNN_DLC float Qualcomm® SA8775P 6.507 ms 16 - 224 MB NPU
decoder QNN_DLC float Qualcomm® SA8775P 6.507 ms 16 - 224 MB NPU
decoder QNN_DLC float Qualcomm® SA7255P 12.66 ms 16 - 201 MB NPU
decoder QNN_DLC float Qualcomm® QCS8450 (Proxy) 9.947 ms 4 - 221 MB NPU
decoder QNN_DLC float Qualcomm® SA8295P 8.158 ms 3 - 196 MB NPU
decoder QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 2.873 ms 4 - 187 MB NPU
decoder QNN_DLC float Qualcomm® QCS9075 6.727 ms 18 - 36 MB NPU
decoder QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.892 ms 1 - 109 MB NPU
decoder QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 1.008 ms 1 - 91 MB NPU
decoder QNN_DLC w8a8 Snapdragon® X2 Elite 1.303 ms 4 - 4 MB NPU
decoder QNN_DLC w8a8 Snapdragon® X Elite 2.352 ms 4 - 4 MB NPU
decoder QNN_DLC w8a8 Snapdragon® X Elite 2.352 ms 4 - 4 MB NPU
decoder QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 1.299 ms 4 - 114 MB NPU
decoder QNN_DLC w8a8 Qualcomm® QCS6490 8.342 ms 1 - 7 MB NPU
decoder QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 2.028 ms 4 - 12 MB NPU
decoder QNN_DLC w8a8 Qualcomm® SA8775P 2.627 ms 4 - 92 MB NPU
decoder QNN_DLC w8a8 Qualcomm® SA8775P 2.627 ms 4 - 92 MB NPU
decoder QNN_DLC w8a8 Qualcomm® SA8775P 2.627 ms 4 - 92 MB NPU
decoder QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 2.531 ms 4 - 213 MB NPU
decoder QNN_DLC w8a8 Qualcomm® QCM6690 10.146 ms 4 - 275 MB NPU
decoder QNN_DLC w8a8 Qualcomm® QCS9075 2.397 ms 1 - 7 MB NPU
decoder QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 1.008 ms 1 - 91 MB NPU
decoder QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 2.547 ms 0 - 111 MB NPU
decoder QNN_DLC w8a8 Qualcomm® SA7255P 3.911 ms 4 - 89 MB NPU
decoder QNN_DLC w8a8 Qualcomm® SA8295P 2.955 ms 4 - 88 MB NPU
decoder QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 2.531 ms 4 - 213 MB NPU
decoder TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 2.61 ms 0 - 188 MB NPU
decoder TFLITE float Snapdragon® 8 Elite Mobile 2.862 ms 0 - 182 MB NPU
decoder TFLITE float Snapdragon® 8 Gen 3 Mobile 3.733 ms 0 - 213 MB NPU
decoder TFLITE float Qualcomm® QCS8550 (Proxy) 5.336 ms 0 - 4 MB NPU
decoder TFLITE float Qualcomm® SA8775P 6.6 ms 0 - 188 MB NPU
decoder TFLITE float Qualcomm® SA8775P 6.6 ms 0 - 188 MB NPU
decoder TFLITE float Qualcomm® SA8775P 6.6 ms 0 - 188 MB NPU
decoder TFLITE float Qualcomm® SA7255P 12.623 ms 0 - 186 MB NPU
decoder TFLITE float Qualcomm® QCS8450 (Proxy) 10.071 ms 0 - 217 MB NPU
decoder TFLITE float Qualcomm® SA8295P 8.261 ms 0 - 195 MB NPU
decoder TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 2.862 ms 0 - 182 MB NPU
decoder TFLITE float Qualcomm® QCS9075 6.793 ms 0 - 30 MB NPU
decoder TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 3.071 ms 0 - 255 MB NPU
decoder TFLITE w8a8 Snapdragon® 8 Elite Mobile 3.527 ms 0 - 239 MB NPU
decoder TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 5.802 ms 0 - 264 MB NPU
decoder TFLITE w8a8 Qualcomm® QCS6490 36.871 ms 12 - 58 MB NPU
decoder TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 7.702 ms 0 - 32 MB NPU
decoder TFLITE w8a8 Qualcomm® SA8775P 8.615 ms 0 - 240 MB NPU
decoder TFLITE w8a8 Qualcomm® SA8775P 8.615 ms 0 - 240 MB NPU
decoder TFLITE w8a8 Qualcomm® SA8775P 8.615 ms 0 - 240 MB NPU
decoder TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 14.329 ms 12 - 203 MB NPU
decoder TFLITE w8a8 Qualcomm® QCM6690 32.841 ms 12 - 211 MB NPU
decoder TFLITE w8a8 Qualcomm® QCS9075 8.483 ms 0 - 14 MB NPU
decoder TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 3.527 ms 0 - 239 MB NPU
decoder TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 10.139 ms 0 - 248 MB NPU
decoder TFLITE w8a8 Qualcomm® SA7255P 13.54 ms 0 - 238 MB NPU
decoder TFLITE w8a8 Qualcomm® SA8295P 9.441 ms 0 - 239 MB NPU
decoder TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 14.329 ms 12 - 203 MB NPU
encoder ONNX float Snapdragon® 8 Elite Gen 5 Mobile 7.813 ms 45 - 329 MB NPU
encoder ONNX float Snapdragon® 8 Elite Mobile 9.928 ms 33 - 308 MB NPU
encoder ONNX float Snapdragon® X2 Elite 8.901 ms 32 - 32 MB NPU
encoder ONNX float Snapdragon® X Elite 20.208 ms 34 - 34 MB NPU
encoder ONNX float Snapdragon® X Elite 20.208 ms 34 - 34 MB NPU
encoder ONNX float Snapdragon® 8 Gen 3 Mobile 15.205 ms 0 - 350 MB NPU
encoder ONNX float Qualcomm® QCS8550 (Proxy) 20.383 ms 28 - 44 MB NPU
encoder ONNX float Snapdragon® 8 Elite For Galaxy Mobile 9.928 ms 33 - 308 MB NPU
encoder ONNX float Qualcomm® QCS9075 29.555 ms 12 - 26 MB NPU
encoder ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 3.293 ms 4 - 279 MB NPU
encoder ONNX w8a8 Snapdragon® 8 Elite Mobile 4.436 ms 10 - 273 MB NPU
encoder ONNX w8a8 Snapdragon® X2 Elite 3.476 ms 18 - 18 MB NPU
encoder ONNX w8a8 Snapdragon® X Elite 8.945 ms 16 - 16 MB NPU
encoder ONNX w8a8 Snapdragon® X Elite 8.945 ms 16 - 16 MB NPU
encoder ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 5.476 ms 12 - 323 MB NPU
encoder ONNX w8a8 Qualcomm® QCS6490 481.51 ms 203 - 213 MB CPU
encoder ONNX w8a8 Qualcomm® QCS8550 (Proxy) 8.216 ms 11 - 16 MB NPU
encoder ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 305.0 ms 139 - 151 MB CPU
encoder ONNX w8a8 Qualcomm® QCM6690 322.955 ms 206 - 218 MB CPU
encoder ONNX w8a8 Qualcomm® QCS9075 9.395 ms 12 - 15 MB NPU
encoder ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 4.436 ms 10 - 273 MB NPU
encoder ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 305.0 ms 139 - 151 MB CPU
encoder QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 8.846 ms 12 - 309 MB NPU
encoder QNN_DLC float Snapdragon® 8 Elite Mobile 11.822 ms 10 - 288 MB NPU
encoder QNN_DLC float Snapdragon® X2 Elite 10.503 ms 12 - 12 MB NPU
encoder QNN_DLC float Snapdragon® X Elite 24.087 ms 12 - 12 MB NPU
encoder QNN_DLC float Snapdragon® X Elite 24.087 ms 12 - 12 MB NPU
encoder QNN_DLC float Snapdragon® 8 Gen 3 Mobile 17.093 ms 12 - 374 MB NPU
encoder QNN_DLC float Qualcomm® QCS8550 (Proxy) 23.75 ms 12 - 15 MB NPU
encoder QNN_DLC float Qualcomm® SA8775P 28.046 ms 1 - 280 MB NPU
encoder QNN_DLC float Qualcomm® SA8775P 28.046 ms 1 - 280 MB NPU
encoder QNN_DLC float Qualcomm® SA8775P 28.046 ms 1 - 280 MB NPU
encoder QNN_DLC float Qualcomm® SA7255P 69.75 ms 0 - 280 MB NPU
encoder QNN_DLC float Qualcomm® QCS8450 (Proxy) 93.578 ms 0 - 435 MB NPU
encoder QNN_DLC float Qualcomm® SA8295P 56.695 ms 0 - 358 MB NPU
encoder QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 11.822 ms 10 - 288 MB NPU
encoder QNN_DLC float Qualcomm® QCS9075 34.392 ms 12 - 42 MB NPU
encoder QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 4.225 ms 3 - 273 MB NPU
encoder QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 5.355 ms 3 - 259 MB NPU
encoder QNN_DLC w8a8 Snapdragon® X2 Elite 4.814 ms 3 - 3 MB NPU
encoder QNN_DLC w8a8 Snapdragon® X Elite 12.117 ms 3 - 3 MB NPU
encoder QNN_DLC w8a8 Snapdragon® X Elite 12.117 ms 3 - 3 MB NPU
encoder QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 7.537 ms 3 - 320 MB NPU
encoder QNN_DLC w8a8 Qualcomm® QCS6490 3536.217 ms 1 - 10 MB NPU
encoder QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 11.346 ms 3 - 5 MB NPU
encoder QNN_DLC w8a8 Qualcomm® SA8775P 12.064 ms 3 - 268 MB NPU
encoder QNN_DLC w8a8 Qualcomm® SA8775P 12.064 ms 3 - 268 MB NPU
encoder QNN_DLC w8a8 Qualcomm® SA8775P 12.064 ms 3 - 268 MB NPU
encoder QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 12.373 ms 3 - 300 MB NPU
encoder QNN_DLC w8a8 Qualcomm® QCM6690 58.735 ms 3 - 270 MB NPU
encoder QNN_DLC w8a8 Qualcomm® QCS9075 14.531 ms 3 - 12 MB NPU
encoder QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 5.355 ms 3 - 259 MB NPU
encoder QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 1950.998 ms 3 - 207 MB NPU
encoder QNN_DLC w8a8 Qualcomm® SA7255P 20.387 ms 3 - 267 MB NPU
encoder QNN_DLC w8a8 Qualcomm® SA8295P 1984.018 ms 3 - 162 MB NPU
encoder QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 12.373 ms 3 - 300 MB NPU
encoder TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 8.655 ms 16 - 321 MB NPU
encoder TFLITE float Snapdragon® 8 Elite Mobile 11.437 ms 14 - 301 MB NPU
encoder TFLITE float Snapdragon® 8 Gen 3 Mobile 16.567 ms 15 - 366 MB NPU
encoder TFLITE float Qualcomm® QCS8550 (Proxy) 23.013 ms 16 - 18 MB NPU
encoder TFLITE float Qualcomm® SA8775P 27.372 ms 16 - 287 MB NPU
encoder TFLITE float Qualcomm® SA8775P 27.372 ms 16 - 287 MB NPU
encoder TFLITE float Qualcomm® SA8775P 27.372 ms 16 - 287 MB NPU
encoder TFLITE float Qualcomm® SA7255P 68.116 ms 16 - 289 MB NPU
encoder TFLITE float Qualcomm® QCS8450 (Proxy) 97.078 ms 16 - 438 MB NPU
encoder TFLITE float Qualcomm® SA8295P 53.478 ms 16 - 366 MB NPU
encoder TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 11.437 ms 14 - 301 MB NPU
encoder TFLITE float Qualcomm® QCS9075 33.739 ms 0 - 42 MB NPU
encoder TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 4.141 ms 4 - 263 MB NPU
encoder TFLITE w8a8 Snapdragon® 8 Elite Mobile 3.006 ms 3 - 254 MB NPU
encoder TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 4.761 ms 3 - 302 MB NPU
encoder TFLITE w8a8 Qualcomm® QCS6490 3169.203 ms 4 - 26 MB NPU
encoder TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 7.004 ms 4 - 6 MB NPU
encoder TFLITE w8a8 Qualcomm® SA8775P 7.798 ms 4 - 261 MB NPU
encoder TFLITE w8a8 Qualcomm® SA8775P 7.798 ms 4 - 261 MB NPU
encoder TFLITE w8a8 Qualcomm® SA8775P 7.798 ms 4 - 261 MB NPU
encoder TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 8.141 ms 3 - 260 MB NPU
encoder TFLITE w8a8 Qualcomm® QCM6690 47.682 ms 4 - 236 MB NPU
encoder TFLITE w8a8 Qualcomm® QCS9075 7.93 ms 4 - 19 MB NPU
encoder TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 3.006 ms 3 - 254 MB NPU
encoder TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 2249.565 ms 1 - 330 MB NPU
encoder TFLITE w8a8 Qualcomm® SA7255P 13.739 ms 4 - 261 MB NPU
encoder TFLITE w8a8 Qualcomm® SA8295P 2103.029 ms 0 - 281 MB NPU
encoder TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 8.141 ms 3 - 260 MB NPU

License

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

References

Community

Downloads last month

-

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

Paper for qualcomm/EdgeTAM