Segment-Anything-Model-2: Optimized for Qualcomm Devices
SAM 2, the successor to Meta's Segment Anything Model (SAM), is a cutting-edge tool designed for comprehensive object segmentation in both images and videos. It excels in handling complex visual data through a unified, promptable model architecture that supports real-time processing and zero-shot generalization.
This is based on the implementation of Segment-Anything-Model-2 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 1.25.0 | Download |
| ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| QNN_DLC | float | Universal | QAIRT 2.45 | Download |
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | Download |
| TFLITE | w8a8 | Universal | QAIRT 2.45 | Download |
For more device-specific assets and performance metrics, visit Segment-Anything-Model-2 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 Segment-Anything-Model-2 on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.semantic_segmentation
Model Stats:
- Model checkpoint: sam2.1_hiera_t
- Input resolution: 720p (720x1280)
- Number of parameters (encoder): 33.5M
- Model size (encoder) (float): 128 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® X2 Elite | 3.301 ms | 16 - 16 MB | NPU |
| decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 4.756 ms | 2 - 243 MB | NPU |
| decoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.758 ms | 16 - 20 MB | NPU |
| decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.182 ms | 1 - 221 MB | NPU |
| decoder | ONNX | float | Snapdragon® 8 Elite Mobile | 3.748 ms | 1 - 223 MB | NPU |
| decoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 3.748 ms | 1 - 223 MB | NPU |
| decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 8.242 ms | 16 - 61 MB | NPU |
| decoder | ONNX | w8a8 | Snapdragon® X2 Elite | 1.331 ms | 4 - 4 MB | NPU |
| decoder | ONNX | w8a8 | Snapdragon® X Elite | 2.737 ms | 4 - 4 MB | NPU |
| decoder | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.777 ms | 4 - 163 MB | NPU |
| decoder | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 3.507 ms | 4 - 165 MB | NPU |
| decoder | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 12.713 ms | 4 - 7 MB | NPU |
| decoder | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.614 ms | 2 - 8 MB | NPU |
| decoder | ONNX | w8a8 | Qualcomm® QCS8450 | 3.507 ms | 4 - 165 MB | NPU |
| decoder | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 1.428 ms | 0 - 130 MB | NPU |
| decoder | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 3.372 ms | 4 - 301 MB | NPU |
| decoder | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.248 ms | 1 - 157 MB | NPU |
| decoder | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 3.186 ms | 4 - 7 MB | NPU |
| decoder | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 15.968 ms | 2 - 254 MB | NPU |
| decoder | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 3.372 ms | 4 - 301 MB | NPU |
| decoder | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 1.428 ms | 0 - 130 MB | NPU |
| decoder | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 2.737 ms | 4 - 4 MB | NPU |
| decoder | QNN_DLC | float | Snapdragon® X2 Elite | 3.092 ms | 16 - 16 MB | NPU |
| decoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.714 ms | 4 - 216 MB | NPU |
| decoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 10.004 ms | 4 - 217 MB | NPU |
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.378 ms | 16 - 20 MB | NPU |
| decoder | QNN_DLC | float | Qualcomm® QCS8450 | 10.004 ms | 4 - 217 MB | NPU |
| decoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.594 ms | 4 - 192 MB | NPU |
| decoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.94 ms | 1 - 189 MB | NPU |
| decoder | QNN_DLC | float | Qualcomm® SA8295P | 8.214 ms | 0 - 195 MB | NPU |
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.94 ms | 1 - 189 MB | NPU |
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 6.682 ms | 16 - 34 MB | NPU |
| decoder | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 1.315 ms | 4 - 4 MB | NPU |
| decoder | QNN_DLC | w8a8 | Snapdragon® X Elite | 2.235 ms | 4 - 4 MB | NPU |
| decoder | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.292 ms | 0 - 109 MB | NPU |
| decoder | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.595 ms | 0 - 109 MB | NPU |
| decoder | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 9.851 ms | 1 - 7 MB | NPU |
| decoder | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.954 ms | 4 - 20 MB | NPU |
| decoder | QNN_DLC | w8a8 | Qualcomm® SA8775P | 2.639 ms | 4 - 92 MB | NPU |
| decoder | QNN_DLC | w8a8 | Qualcomm® SA8650P | 2.639 ms | 4 - 92 MB | NPU |
| decoder | QNN_DLC | w8a8 | Qualcomm® SA8255P | 2.639 ms | 4 - 92 MB | NPU |
| decoder | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 2.595 ms | 0 - 109 MB | NPU |
| decoder | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 1.018 ms | 1 - 89 MB | NPU |
| decoder | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 2.68 ms | 4 - 212 MB | NPU |
| decoder | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.901 ms | 1 - 109 MB | NPU |
| decoder | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 2.472 ms | 1 - 6 MB | NPU |
| decoder | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 9.938 ms | 4 - 275 MB | NPU |
| decoder | QNN_DLC | w8a8 | Qualcomm® SA8295P | 2.958 ms | 4 - 88 MB | NPU |
| decoder | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 2.68 ms | 4 - 212 MB | NPU |
| decoder | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 1.018 ms | 1 - 89 MB | NPU |
| decoder | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 2.235 ms | 4 - 4 MB | NPU |
| decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.72 ms | 0 - 213 MB | NPU |
| decoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 9.989 ms | 0 - 219 MB | NPU |
| decoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.328 ms | 0 - 8 MB | NPU |
| decoder | TFLITE | float | Qualcomm® SA8775P | 42.72 ms | 0 - 33 MB | GPU |
| decoder | TFLITE | float | Qualcomm® SA8650P | 42.72 ms | 0 - 33 MB | GPU |
| decoder | TFLITE | float | Qualcomm® SA8255P | 42.72 ms | 0 - 33 MB | GPU |
| decoder | TFLITE | float | Qualcomm® QCS8450 | 9.989 ms | 0 - 219 MB | NPU |
| decoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.637 ms | 0 - 184 MB | NPU |
| decoder | TFLITE | float | Qualcomm® SA8295P | 8.184 ms | 0 - 196 MB | NPU |
| decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 6.904 ms | 0 - 30 MB | NPU |
| decoder | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 5.786 ms | 0 - 265 MB | NPU |
| decoder | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 10.177 ms | 0 - 246 MB | NPU |
| decoder | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 39.507 ms | 12 - 58 MB | NPU |
| decoder | TFLITE | w8a8 | Qualcomm® QCS8275 | 67.255 ms | 17 - 52 MB | GPU |
| decoder | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.73 ms | 0 - 28 MB | NPU |
| decoder | TFLITE | w8a8 | Qualcomm® SA8775P | 8.555 ms | 0 - 240 MB | NPU |
| decoder | TFLITE | w8a8 | Qualcomm® SA8650P | 8.555 ms | 0 - 240 MB | NPU |
| decoder | TFLITE | w8a8 | Qualcomm® SA8255P | 8.555 ms | 0 - 240 MB | NPU |
| decoder | TFLITE | w8a8 | Qualcomm® QCS8450 | 10.177 ms | 0 - 246 MB | NPU |
| decoder | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 3.514 ms | 0 - 240 MB | NPU |
| decoder | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 14.337 ms | 12 - 201 MB | NPU |
| decoder | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.121 ms | 0 - 255 MB | NPU |
| decoder | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 8.262 ms | 0 - 14 MB | NPU |
| decoder | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 32.784 ms | 13 - 210 MB | NPU |
| decoder | TFLITE | w8a8 | Qualcomm® SA8295P | 9.455 ms | 0 - 239 MB | NPU |
| decoder | TFLITE | w8a8 | Qualcomm® SA7255P | 67.255 ms | 17 - 52 MB | GPU |
| decoder | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 14.337 ms | 12 - 201 MB | NPU |
| decoder | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 3.514 ms | 0 - 240 MB | NPU |
| encoder | ONNX | float | Snapdragon® X2 Elite | 86.851 ms | 70 - 70 MB | NPU |
| encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 126.384 ms | 58 - 2157 MB | NPU |
| encoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 168.886 ms | 8 - 95 MB | NPU |
| encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 78.771 ms | 45 - 1714 MB | NPU |
| encoder | ONNX | float | Snapdragon® 8 Elite Mobile | 97.703 ms | 44 - 1798 MB | NPU |
| encoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 97.703 ms | 44 - 1798 MB | NPU |
| encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 226.812 ms | 12 - 69 MB | NPU |
| encoder | ONNX | w8a8 | Snapdragon® X2 Elite | 35.618 ms | 18 - 18 MB | NPU |
| encoder | ONNX | w8a8 | Snapdragon® X Elite | 91.477 ms | 52 - 52 MB | NPU |
| encoder | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 63.775 ms | 16 - 1945 MB | NPU |
| encoder | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 124.433 ms | 0 - 2391 MB | NPU |
| encoder | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 676.253 ms | 6 - 12 MB | NPU |
| encoder | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 87.71 ms | 0 - 57 MB | NPU |
| encoder | ONNX | w8a8 | Qualcomm® QCS8450 | 124.433 ms | 0 - 2391 MB | NPU |
| encoder | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 39.644 ms | 11 - 2123 MB | NPU |
| encoder | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 88.7 ms | 14 - 2358 MB | NPU |
| encoder | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 34.125 ms | 12 - 1680 MB | NPU |
| encoder | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 74.824 ms | 11 - 17 MB | NPU |
| encoder | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 1257.361 ms | 3 - 1934 MB | NPU |
| encoder | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 88.7 ms | 14 - 2358 MB | NPU |
| encoder | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 39.644 ms | 11 - 2123 MB | NPU |
| encoder | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 91.477 ms | 52 - 52 MB | NPU |
| encoder | QNN_DLC | float | Snapdragon® X2 Elite | 85.915 ms | 12 - 12 MB | NPU |
| encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 128.059 ms | 12 - 2146 MB | NPU |
| encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 341.96 ms | 13 - 1861 MB | NPU |
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 179.716 ms | 9 - 16 MB | NPU |
| encoder | QNN_DLC | float | Qualcomm® QCS8450 | 341.96 ms | 13 - 1861 MB | NPU |
| encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 78.373 ms | 0 - 1706 MB | NPU |
| encoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 100.862 ms | 11 - 2522 MB | NPU |
| encoder | QNN_DLC | float | Qualcomm® SA8295P | 282.738 ms | 1 - 1582 MB | NPU |
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 100.862 ms | 11 - 2522 MB | NPU |
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 218.985 ms | 12 - 46 MB | NPU |
| encoder | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 36.559 ms | 3 - 3 MB | NPU |
| encoder | QNN_DLC | w8a8 | Snapdragon® X Elite | 83.578 ms | 3 - 3 MB | NPU |
| encoder | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 54.844 ms | 3 - 1883 MB | NPU |
| encoder | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 136.835 ms | 3 - 1897 MB | NPU |
| encoder | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 678.591 ms | 3 - 13 MB | NPU |
| encoder | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 80.452 ms | 3 - 6 MB | NPU |
| encoder | QNN_DLC | w8a8 | Qualcomm® SA8775P | 81.912 ms | 3 - 1580 MB | NPU |
| encoder | QNN_DLC | w8a8 | Qualcomm® SA8650P | 81.912 ms | 3 - 1580 MB | NPU |
| encoder | QNN_DLC | w8a8 | Qualcomm® SA8255P | 81.912 ms | 3 - 1580 MB | NPU |
| encoder | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 136.835 ms | 3 - 1897 MB | NPU |
| encoder | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 40.06 ms | 3 - 1633 MB | NPU |
| encoder | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 95.72 ms | 3 - 2356 MB | NPU |
| encoder | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 35.363 ms | 3 - 1663 MB | NPU |
| encoder | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 106.438 ms | 1 - 10 MB | NPU |
| encoder | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 1253.567 ms | 3 - 1919 MB | NPU |
| encoder | QNN_DLC | w8a8 | Qualcomm® SA8295P | 95.717 ms | 0 - 1591 MB | NPU |
| encoder | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 95.72 ms | 3 - 2356 MB | NPU |
| encoder | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 40.06 ms | 3 - 1633 MB | NPU |
| encoder | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 83.578 ms | 3 - 3 MB | NPU |
| encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 129.64 ms | 20 - 2227 MB | NPU |
| encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 347.74 ms | 21 - 1955 MB | NPU |
| encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 180.195 ms | 20 - 23 MB | NPU |
| encoder | TFLITE | float | Qualcomm® SA8775P | 2416.888 ms | 39 - 65 MB | CPU |
| encoder | TFLITE | float | Qualcomm® SA8650P | 2416.888 ms | 39 - 65 MB | CPU |
| encoder | TFLITE | float | Qualcomm® SA8255P | 2416.888 ms | 39 - 65 MB | CPU |
| encoder | TFLITE | float | Qualcomm® QCS8450 | 347.74 ms | 21 - 1955 MB | NPU |
| encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 76.287 ms | 20 - 1777 MB | NPU |
| encoder | TFLITE | float | Qualcomm® SA8295P | 282.438 ms | 20 - 1665 MB | NPU |
| encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 218.941 ms | 0 - 114 MB | NPU |
| encoder | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 70.211 ms | 5 - 2224 MB | NPU |
| encoder | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 183.213 ms | 5 - 2292 MB | NPU |
| encoder | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1720.565 ms | 76 - 339 MB | CPU |
| encoder | TFLITE | w8a8 | Qualcomm® QCS8275 | 162.746 ms | 6 - 1878 MB | NPU |
| encoder | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 101.03 ms | 5 - 10 MB | NPU |
| encoder | TFLITE | w8a8 | Qualcomm® SA8775P | 97.994 ms | 6 - 1877 MB | NPU |
| encoder | TFLITE | w8a8 | Qualcomm® SA8650P | 97.994 ms | 6 - 1877 MB | NPU |
| encoder | TFLITE | w8a8 | Qualcomm® SA8255P | 97.994 ms | 6 - 1877 MB | NPU |
| encoder | TFLITE | w8a8 | Qualcomm® QCS8450 | 183.213 ms | 5 - 2292 MB | NPU |
| encoder | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 56.455 ms | 4 - 1791 MB | NPU |
| encoder | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1123.658 ms | 28 - 256 MB | CPU |
| encoder | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 34.4 ms | 5 - 1795 MB | NPU |
| encoder | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 96.155 ms | 3 - 69 MB | NPU |
| encoder | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 2367.706 ms | 78 - 312 MB | CPU |
| encoder | TFLITE | w8a8 | Qualcomm® SA8295P | 118.048 ms | 5 - 1882 MB | NPU |
| encoder | TFLITE | w8a8 | Qualcomm® SA7255P | 162.746 ms | 6 - 1878 MB | NPU |
| encoder | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1123.658 ms | 28 - 256 MB | CPU |
| encoder | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 56.455 ms | 4 - 1791 MB | NPU |
License
- The license for the original implementation of Segment-Anything-Model-2 can be found here.
References
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.
