README.md

---
library_name: pytorch
license: other
tags:
- android
pipeline_tag: image-segmentation

---

![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/web-assets/model_demo.png)

# FastSam-X: 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-X found [here](https://github.com/CASIA-IVA-Lab/FastSAM).
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/fastsam_x) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).

Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) 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 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.47.0/fastsam_x-onnx-float.zip)
| QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.47.0/fastsam_x-qnn_dlc-float.zip)
| TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.47.0/fastsam_x-tflite-float.zip)

For more device-specific assets and performance metrics, visit **[FastSam-X on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/fastsam_x)**.


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/fastsam_x) 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-X on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/fastsam_x) for usage instructions.

## Model Details

**Model Type:** Model_use_case.semantic_segmentation

**Model Stats:**
- Model checkpoint: fastsam-x.pt
- Inference latency: RealTime
- Input resolution: 640x640
- Number of parameters: 72.2M
- Model size (float): 276 MB

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| FastSam-X | ONNX | float | Snapdragon® X Elite | 46.589 ms | 138 - 138 MB | NPU
| FastSam-X | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 36.036 ms | 2 - 326 MB | NPU
| FastSam-X | ONNX | float | Qualcomm® QCS8550 (Proxy) | 45.784 ms | 0 - 172 MB | NPU
| FastSam-X | ONNX | float | Qualcomm® QCS9075 | 74.387 ms | 12 - 20 MB | NPU
| FastSam-X | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 27.414 ms | 12 - 251 MB | NPU
| FastSam-X | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 18.188 ms | 16 - 263 MB | NPU
| FastSam-X | ONNX | float | Snapdragon® X2 Elite | 23.84 ms | 139 - 139 MB | NPU
| FastSam-X | QNN_DLC | float | Snapdragon® X Elite | 43.795 ms | 5 - 5 MB | NPU
| FastSam-X | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 32.529 ms | 3 - 305 MB | NPU
| FastSam-X | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 279.714 ms | 2 - 219 MB | NPU
| FastSam-X | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 42.252 ms | 5 - 6 MB | NPU
| FastSam-X | QNN_DLC | float | Qualcomm® SA8775P | 68.418 ms | 1 - 216 MB | NPU
| FastSam-X | QNN_DLC | float | Qualcomm® QCS9075 | 70.808 ms | 7 - 17 MB | NPU
| FastSam-X | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 91.805 ms | 4 - 398 MB | NPU
| FastSam-X | QNN_DLC | float | Qualcomm® SA7255P | 279.714 ms | 2 - 219 MB | NPU
| FastSam-X | QNN_DLC | float | Qualcomm® SA8295P | 77.494 ms | 0 - 296 MB | NPU
| FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 25.399 ms | 0 - 217 MB | NPU
| FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.291 ms | 4 - 227 MB | NPU
| FastSam-X | QNN_DLC | float | Snapdragon® X2 Elite | 22.975 ms | 5 - 5 MB | NPU
| FastSam-X | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 32.536 ms | 2 - 436 MB | NPU
| FastSam-X | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 279.272 ms | 5 - 264 MB | NPU
| FastSam-X | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 42.161 ms | 4 - 39 MB | NPU
| FastSam-X | TFLITE | float | Qualcomm® SA8775P | 67.904 ms | 4 - 265 MB | NPU
| FastSam-X | TFLITE | float | Qualcomm® QCS9075 | 70.046 ms | 4 - 158 MB | NPU
| FastSam-X | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 91.847 ms | 5 - 526 MB | NPU
| FastSam-X | TFLITE | float | Qualcomm® SA7255P | 279.272 ms | 5 - 264 MB | NPU
| FastSam-X | TFLITE | float | Qualcomm® SA8295P | 76.853 ms | 0 - 339 MB | NPU
| FastSam-X | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 25.236 ms | 4 - 271 MB | NPU
| FastSam-X | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.065 ms | 2 - 268 MB | NPU

## License
* The license for the original implementation of FastSam-X can be found
  [here](https://github.com/CASIA-IVA-Lab/FastSAM/blob/main/LICENSE).

## References
* [Fast Segment Anything](https://arxiv.org/abs/2306.12156)
* [Source Model Implementation](https://github.com/CASIA-IVA-Lab/FastSAM)

## Community
* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).