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

---

![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/web-assets/model_demo.png)

# Segment-Anything-Model-2: Optimized for Mobile Deployment
## High-quality segmentation in images and videos with real-time performance and minimal user interaction


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 model is an implementation of Segment-Anything-Model-2 found [here](https://github.com/facebookresearch/sam2).


This repository provides scripts to run Segment-Anything-Model-2 on Qualcomm® devices.
More details on model performance across various devices, can be found
[here](https://aihub.qualcomm.com/models/sam2).



### Model Details

- **Model Type:** Model_use_case.semantic_segmentation
- **Model Stats:**
  - Model checkpoint: sam2.1_hiera_t
  - Input resolution: 720p (720x1280)
  - Number of parameters (SAM2Encoder): 33.5M
  - Model size (SAM2Encoder) (float): 128 MB
  - Number of parameters (SAM2Decoder): 6.22M
  - Model size (SAM2Decoder) (float): 23.7 MB

| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|---|---|---|---|---|---|---|---|---|
| SAM2Encoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 572.014 ms | 16 - 1186 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Encoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 468.456 ms | 1 - 849 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Encoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 346.409 ms | 16 - 2444 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Encoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 392.85 ms | 12 - 2690 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Encoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 259.846 ms | 16 - 91 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Encoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 215.389 ms | 12 - 95 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Encoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 274.742 ms | 16 - 1185 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Encoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 226.155 ms | 1 - 848 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Encoder | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 572.014 ms | 16 - 1186 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Encoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 468.456 ms | 1 - 849 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Encoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 260.793 ms | 0 - 76 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Encoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 215.948 ms | 12 - 93 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Encoder | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 377.929 ms | 10 - 1142 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Encoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 261.634 ms | 13 - 89 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Encoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 215.622 ms | 12 - 94 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Encoder | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 274.742 ms | 16 - 1185 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Encoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 226.155 ms | 1 - 848 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Encoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 191.439 ms | 367 - 2755 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Encoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 162.155 ms | 12 - 866 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Encoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 157.237 ms | 16 - 1267 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Encoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 129.536 ms | 0 - 825 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Encoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 101.626 ms | 12 - 832 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Encoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 204.047 ms | 257 - 257 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Decoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 14.135 ms | 0 - 47 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Decoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 12.378 ms | 4 - 56 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Decoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 8.427 ms | 0 - 55 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Decoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 13.734 ms | 15 - 68 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Decoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 5.956 ms | 0 - 30 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Decoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 5.228 ms | 16 - 30 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Decoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 7.244 ms | 0 - 46 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Decoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.619 ms | 9 - 64 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Decoder | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 14.135 ms | 0 - 47 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Decoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 12.378 ms | 4 - 56 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Decoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 5.908 ms | 0 - 27 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Decoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 5.317 ms | 16 - 31 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Decoder | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 9.565 ms | 0 - 51 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Decoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 5.911 ms | 0 - 27 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Decoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 5.27 ms | 16 - 32 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Decoder | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 7.244 ms | 0 - 46 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Decoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 6.619 ms | 9 - 64 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Decoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 4.152 ms | 0 - 59 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Decoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 3.635 ms | 0 - 66 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Decoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 3.478 ms | 0 - 52 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.tflite) |
| SAM2Decoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 2.948 ms | 4 - 72 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Decoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 2.541 ms | 4 - 58 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Decoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 5.38 ms | 16 - 16 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2.dlc) |
| SAM2Encoder | w8a8 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | TFLITE | 1800.373 ms | 94 - 345 MB | CPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Encoder | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 227.055 ms | 4 - 881 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Encoder | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 152.582 ms | 3 - 1057 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Encoder | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 138.365 ms | 4 - 1100 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Encoder | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 154.449 ms | 3 - 1304 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Encoder | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 128.198 ms | 3 - 117 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Encoder | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 95.554 ms | 0 - 127 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Encoder | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 132.127 ms | 4 - 881 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Encoder | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 392.19 ms | 3 - 1059 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Encoder | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 227.055 ms | 4 - 881 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Encoder | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 152.582 ms | 3 - 1057 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Encoder | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 131.016 ms | 0 - 115 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Encoder | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 95.931 ms | 0 - 124 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Encoder | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 152.807 ms | 4 - 886 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Encoder | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 108.714 ms | 3 - 1056 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Encoder | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 130.365 ms | 0 - 115 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Encoder | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 96.397 ms | 0 - 130 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Encoder | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 132.127 ms | 4 - 881 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Encoder | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 392.19 ms | 3 - 1059 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Encoder | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 93.019 ms | 31 - 998 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Encoder | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 66.604 ms | 3 - 1161 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Encoder | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 75.695 ms | 4 - 891 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Encoder | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 49.705 ms | 3 - 1029 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Encoder | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | TFLITE | 1274.738 ms | 57 - 286 MB | CPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Encoder | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_DLC | 128.143 ms | 3 - 1637 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Encoder | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 71.451 ms | 3 - 922 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Encoder | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 45.811 ms | 3 - 1578 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Encoder | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 96.825 ms | 178 - 178 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Decoder | w8a8 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | TFLITE | 49.235 ms | 12 - 58 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Decoder | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 21.774 ms | 0 - 63 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Decoder | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 3.834 ms | 4 - 56 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Decoder | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 14.248 ms | 0 - 75 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Decoder | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 2.632 ms | 4 - 68 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Decoder | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 12.858 ms | 0 - 49 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Decoder | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 1.942 ms | 4 - 20 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Decoder | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 13.557 ms | 0 - 63 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Decoder | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 2.539 ms | 4 - 56 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Decoder | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 21.774 ms | 0 - 63 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Decoder | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 3.834 ms | 4 - 56 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Decoder | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 12.836 ms | 0 - 53 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Decoder | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 1.948 ms | 4 - 16 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Decoder | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 15.062 ms | 0 - 66 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Decoder | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 2.897 ms | 4 - 62 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Decoder | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 13.019 ms | 0 - 49 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Decoder | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 1.943 ms | 4 - 17 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Decoder | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 13.557 ms | 0 - 63 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Decoder | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 2.539 ms | 4 - 56 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Decoder | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 9.756 ms | 0 - 73 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Decoder | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.259 ms | 1 - 62 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Decoder | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 8.021 ms | 0 - 69 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Decoder | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 0.995 ms | 1 - 60 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Decoder | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | TFLITE | 16.798 ms | 14 - 56 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Decoder | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_DLC | 2.722 ms | 4 - 64 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Decoder | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 7.813 ms | 0 - 65 MB | NPU | [Segment-Anything-Model-2.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.tflite) |
| SAM2Decoder | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 0.899 ms | 1 - 64 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |
| SAM2Decoder | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 2.296 ms | 22 - 22 MB | NPU | [Segment-Anything-Model-2.dlc](https://huggingface.co/qualcomm/Segment-Anything-Model-2/blob/main/Segment-Anything-Model-2_w8a8.dlc) |




## Installation


Install the package via pip:
```bash
# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
pip install "qai-hub-models[sam2]" git+https://github.com/facebookresearch/sam2.git@2b90b9f
```


## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device

Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.com/) with your
Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.

With this API token, you can configure your client to run models on the cloud
hosted devices.
```bash
qai-hub configure --api_token API_TOKEN
```
Navigate to [docs](https://workbench.aihub.qualcomm.com/docs/) for more information.



## Demo off target

The package contains a simple end-to-end demo that downloads pre-trained
weights and runs this model on a sample input.

```bash
python -m qai_hub_models.models.sam2.demo
```

The above demo runs a reference implementation of pre-processing, model
inference, and post processing.

**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
environment, please add the following to your cell (instead of the above).
```
%run -m qai_hub_models.models.sam2.demo
```


### Run model on a cloud-hosted device

In addition to the demo, you can also run the model on a cloud-hosted Qualcomm®
device. This script does the following:
* Performance check on-device on a cloud-hosted device
* Downloads compiled assets that can be deployed on-device for Android.
* Accuracy check between PyTorch and on-device outputs.

```bash
python -m qai_hub_models.models.sam2.export
```



## How does this work?

This [export script](https://aihub.qualcomm.com/models/sam2/qai_hub_models/models/Segment-Anything-Model-2/export.py)
leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model
on-device. Lets go through each step below in detail:

Step 1: **Compile model for on-device deployment**

To compile a PyTorch model for on-device deployment, we first trace the model
in memory using the `jit.trace` and then call the `submit_compile_job` API.

```python
import torch

import qai_hub as hub
from qai_hub_models.models.sam2 import Model

# Load the model
torch_model = Model.from_pretrained()

# Device
device = hub.Device("Samsung Galaxy S25")

# Trace model
input_shape = torch_model.get_input_spec()
sample_inputs = torch_model.sample_inputs()

pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])

# Compile model on a specific device
compile_job = hub.submit_compile_job(
    model=pt_model,
    device=device,
    input_specs=torch_model.get_input_spec(),
)

# Get target model to run on-device
target_model = compile_job.get_target_model()

```


Step 2: **Performance profiling on cloud-hosted device**

After compiling models from step 1. Models can be profiled model on-device using the
`target_model`. Note that this scripts runs the model on a device automatically
provisioned in the cloud.  Once the job is submitted, you can navigate to a
provided job URL to view a variety of on-device performance metrics.
```python
profile_job = hub.submit_profile_job(
    model=target_model,
    device=device,
)
        
```

Step 3: **Verify on-device accuracy**

To verify the accuracy of the model on-device, you can run on-device inference
on sample input data on the same cloud hosted device.
```python
input_data = torch_model.sample_inputs()
inference_job = hub.submit_inference_job(
    model=target_model,
    device=device,
    inputs=input_data,
)
    on_device_output = inference_job.download_output_data()

```
With the output of the model, you can compute like PSNR, relative errors or
spot check the output with expected output.

**Note**: This on-device profiling and inference requires access to Qualcomm®
AI Hub Workbench. [Sign up for access](https://myaccount.qualcomm.com/signup).



## Run demo on a cloud-hosted device

You can also run the demo on-device.

```bash
python -m qai_hub_models.models.sam2.demo --eval-mode on-device
```

**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
environment, please add the following to your cell (instead of the above).
```
%run -m qai_hub_models.models.sam2.demo -- --eval-mode on-device
```


## Deploying compiled model to Android


The models can be deployed using multiple runtimes:
- TensorFlow Lite (`.tflite` export): [This
  tutorial](https://www.tensorflow.org/lite/android/quickstart) provides a
  guide to deploy the .tflite model in an Android application.


- QNN (`.so` export ): This [sample
  app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html)
provides instructions on how to use the `.so` shared library  in an Android application.


## View on Qualcomm® AI Hub
Get more details on Segment-Anything-Model-2's performance across various devices [here](https://aihub.qualcomm.com/models/sam2).
Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)


## License
* The license for the original implementation of Segment-Anything-Model-2 can be found
  [here](https://github.com/facebookresearch/sam2/blob/main/LICENSE).
* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)



## References
* [SAM 2 Segment Anything in Images and Videos](https://arxiv.org/abs/2408.00714)
* [Source Model Implementation](https://github.com/facebookresearch/sam2)



## 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).