Image Segmentation
PyTorch
android

FastSam-S: Optimized for Qualcomm Devices

The Fast Segment Anything Model (FastSAM) is a novel, real-time CNN-based solution for the Segment Anything task. This task is designed to segment any object within an image based on various possible user interaction prompts. The model performs competitively despite significantly reduced computation, making it a practical choice for a variety of vision tasks.

This is based on the implementation of FastSam-S 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
ONNX w8a16 Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a16 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download

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

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

  • Inference latency: RealTime
  • Input resolution: 640x640
  • Model checkpoint: fastsam-s.pt
  • Model size (float): 45.1 MB
  • Number of parameters: 11.8M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
FastSam-S ONNX float Snapdragon® X2 Elite 4.61 ms 17 - 17 MB NPU
FastSam-S ONNX float Snapdragon® X Elite 8.388 ms 21 - 21 MB NPU
FastSam-S ONNX float Snapdragon® 8 Gen 3 Mobile 5.99 ms 18 - 249 MB NPU
FastSam-S ONNX float Snapdragon® 8 Gen 1 Mobile 16.658 ms 17 - 241 MB NPU
FastSam-S ONNX float Qualcomm® Dragonwing™ IQ-8275 13.198 ms 15 - 19 MB NPU
FastSam-S ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 8.228 ms 0 - 25 MB NPU
FastSam-S ONNX float Qualcomm® QCS8450 16.658 ms 17 - 241 MB NPU
FastSam-S ONNX float Qualcomm® Dragonwing™ IQ-9075 11.974 ms 15 - 18 MB NPU
FastSam-S ONNX float Qualcomm® Dragonwing™ IQ-X7181 8.388 ms 21 - 21 MB NPU
FastSam-S ONNX float Qualcomm® Dragonwing™ Q-8750 4.71 ms 12 - 215 MB NPU
FastSam-S ONNX float Snapdragon® 8 Elite Mobile 4.71 ms 12 - 215 MB NPU
FastSam-S ONNX float Snapdragon® 8 Elite Gen 5 Mobile 3.643 ms 3 - 213 MB NPU
FastSam-S ONNX w8a16 Snapdragon® X2 Elite 3.131 ms 9 - 9 MB NPU
FastSam-S ONNX w8a16 Snapdragon® X Elite 7.011 ms 10 - 10 MB NPU
FastSam-S ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 4.373 ms 8 - 264 MB NPU
FastSam-S ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 11.698 ms 9 - 267 MB NPU
FastSam-S ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 27.98 ms 8 - 10 MB NPU
FastSam-S ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 6.455 ms 8 - 11 MB NPU
FastSam-S ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 6.657 ms 0 - 14 MB NPU
FastSam-S ONNX w8a16 Qualcomm® QCS8450 11.698 ms 9 - 267 MB NPU
FastSam-S ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 7.039 ms 8 - 11 MB NPU
FastSam-S ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 7.011 ms 10 - 10 MB NPU
FastSam-S ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 70.828 ms 0 - 257 MB NPU
FastSam-S ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 9.12 ms 8 - 229 MB NPU
FastSam-S ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 3.28 ms 1 - 217 MB NPU
FastSam-S ONNX w8a16 Snapdragon® 8 Elite Mobile 3.28 ms 1 - 217 MB NPU
FastSam-S ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.687 ms 1 - 223 MB NPU
FastSam-S ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 9.12 ms 8 - 229 MB NPU
FastSam-S QNN_DLC float Snapdragon® X2 Elite 4.588 ms 5 - 5 MB NPU
FastSam-S QNN_DLC float Snapdragon® X Elite 8.386 ms 5 - 5 MB NPU
FastSam-S QNN_DLC float Snapdragon® 8 Gen 3 Mobile 5.861 ms 5 - 218 MB NPU
FastSam-S QNN_DLC float Snapdragon® 8 Gen 1 Mobile 15.955 ms 5 - 212 MB NPU
FastSam-S QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 12.88 ms 5 - 16 MB NPU
FastSam-S QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 39.191 ms 0 - 186 MB NPU
FastSam-S QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.794 ms 5 - 14 MB NPU
FastSam-S QNN_DLC float Qualcomm® SA8775P 11.597 ms 1 - 183 MB NPU
FastSam-S QNN_DLC float Qualcomm® SA8650P 11.597 ms 1 - 183 MB NPU
FastSam-S QNN_DLC float Qualcomm® SA8255P 11.597 ms 1 - 183 MB NPU
FastSam-S QNN_DLC float Qualcomm® QCS8450 15.955 ms 5 - 212 MB NPU
FastSam-S QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 11.816 ms 5 - 15 MB NPU
FastSam-S QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 8.386 ms 5 - 5 MB NPU
FastSam-S QNN_DLC float Qualcomm® Dragonwing™ Q-8750 4.477 ms 5 - 195 MB NPU
FastSam-S QNN_DLC float Qualcomm® SA7255P 39.191 ms 0 - 186 MB NPU
FastSam-S QNN_DLC float Qualcomm® SA8295P 13.769 ms 0 - 178 MB NPU
FastSam-S QNN_DLC float Snapdragon® 8 Elite Mobile 4.477 ms 5 - 195 MB NPU
FastSam-S QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 3.253 ms 5 - 197 MB NPU
FastSam-S QNN_DLC w8a16 Snapdragon® X2 Elite 2.859 ms 2 - 2 MB NPU
FastSam-S QNN_DLC w8a16 Snapdragon® X Elite 5.97 ms 2 - 2 MB NPU
FastSam-S QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 3.787 ms 2 - 236 MB NPU
FastSam-S QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 8.28 ms 2 - 233 MB NPU
FastSam-S QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 24.029 ms 1 - 7 MB NPU
FastSam-S QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 5.564 ms 2 - 9 MB NPU
FastSam-S QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 13.386 ms 0 - 193 MB NPU
FastSam-S QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.474 ms 2 - 4 MB NPU
FastSam-S QNN_DLC w8a16 Qualcomm® SA8775P 5.996 ms 1 - 196 MB NPU
FastSam-S QNN_DLC w8a16 Qualcomm® SA8650P 5.996 ms 1 - 196 MB NPU
FastSam-S QNN_DLC w8a16 Qualcomm® SA8255P 5.996 ms 1 - 196 MB NPU
FastSam-S QNN_DLC w8a16 Qualcomm® QCS8450 8.28 ms 2 - 233 MB NPU
FastSam-S QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 6.989 ms 2 - 8 MB NPU
FastSam-S QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 5.97 ms 2 - 2 MB NPU
FastSam-S QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 65.108 ms 2 - 203 MB NPU
FastSam-S QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 7.608 ms 2 - 196 MB NPU
FastSam-S QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 2.66 ms 0 - 198 MB NPU
FastSam-S QNN_DLC w8a16 Qualcomm® SA7255P 13.386 ms 0 - 193 MB NPU
FastSam-S QNN_DLC w8a16 Qualcomm® SA8295P 7.895 ms 0 - 191 MB NPU
FastSam-S QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 2.66 ms 0 - 198 MB NPU
FastSam-S QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.107 ms 2 - 204 MB NPU
FastSam-S QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 7.608 ms 2 - 196 MB NPU
FastSam-S TFLITE float Snapdragon® 8 Gen 3 Mobile 5.164 ms 4 - 118 MB NPU
FastSam-S TFLITE float Snapdragon® 8 Gen 1 Mobile 14.071 ms 6 - 235 MB NPU
FastSam-S TFLITE float Qualcomm® Dragonwing™ IQ-8275 11.963 ms 4 - 40 MB NPU
FastSam-S TFLITE float Qualcomm® Dragonwing™ IQ-8275 37.787 ms 4 - 86 MB NPU
FastSam-S TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 6.973 ms 4 - 7 MB NPU
FastSam-S TFLITE float Qualcomm® SA8775P 10.736 ms 4 - 90 MB NPU
FastSam-S TFLITE float Qualcomm® SA8650P 10.736 ms 4 - 90 MB NPU
FastSam-S TFLITE float Qualcomm® SA8255P 10.736 ms 4 - 90 MB NPU
FastSam-S TFLITE float Qualcomm® QCS8450 14.071 ms 6 - 235 MB NPU
FastSam-S TFLITE float Qualcomm® Dragonwing™ IQ-9075 10.46 ms 4 - 39 MB NPU
FastSam-S TFLITE float Qualcomm® Dragonwing™ Q-8750 3.941 ms 3 - 101 MB NPU
FastSam-S TFLITE float Qualcomm® SA7255P 37.787 ms 4 - 86 MB NPU
FastSam-S TFLITE float Qualcomm® SA8295P 13.077 ms 4 - 195 MB NPU
FastSam-S TFLITE float Snapdragon® 8 Elite Mobile 3.941 ms 3 - 101 MB NPU
FastSam-S TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 3.12 ms 0 - 89 MB NPU

License

  • The license for the original implementation of FastSam-S 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/FastSam-S