Hugging Face's logo

qualcomm
/
YOLOv10-Detection

Object Detection
PyTorch
real_time
android
Model card Files
xet
Community

YOLOv10-Detection: Optimized for Mobile Deployment

Real-time object detection optimized for mobile and edge by Ultralytics

Ultralytics YOLOv10 is a machine learning model that predicts bounding boxes and classes of objects in an image.

This model is an implementation of YOLOv10-Detection found here.

This repository provides scripts to run YOLOv10-Detection on Qualcomm® devices. More details on model performance across various devices, can be found here.

WARNING: The model assets are not readily available for download due to licensing restrictions.

Model Details

  • Model Type: Model_use_case.object_detection
  • Model Stats:
    • Model checkpoint: YOLOv10-N
    • Input resolution: 640x640
    • Number of parameters: 2.33M
    • Model size (float): 8.95 MB
    • Model size (w8a8): 2.55 MB
    • Model size (w8a16): 3.04 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
YOLOv10-Detection float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 13.013 ms 0 - 70 MB NPU --
YOLOv10-Detection float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 12.679 ms 0 - 97 MB NPU --
YOLOv10-Detection float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 7.018 ms 0 - 41 MB NPU --
YOLOv10-Detection float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 7.762 ms 4 - 42 MB NPU --
YOLOv10-Detection float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 3.747 ms 0 - 21 MB NPU --
YOLOv10-Detection float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 3.708 ms 0 - 94 MB NPU --
YOLOv10-Detection float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 5.563 ms 0 - 120 MB NPU --
YOLOv10-Detection float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 5.09 ms 0 - 70 MB NPU --
YOLOv10-Detection float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 5.162 ms 2 - 101 MB NPU --
YOLOv10-Detection float SA7255P ADP Qualcomm® SA7255P TFLITE 13.013 ms 0 - 70 MB NPU --
YOLOv10-Detection float SA7255P ADP Qualcomm® SA7255P QNN_DLC 12.679 ms 0 - 97 MB NPU --
YOLOv10-Detection float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 3.748 ms 0 - 26 MB NPU --
YOLOv10-Detection float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 3.719 ms 0 - 100 MB NPU --
YOLOv10-Detection float SA8295P ADP Qualcomm® SA8295P TFLITE 8.162 ms 0 - 34 MB NPU --
YOLOv10-Detection float SA8295P ADP Qualcomm® SA8295P QNN_DLC 8.053 ms 4 - 39 MB NPU --
YOLOv10-Detection float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 3.751 ms 0 - 23 MB NPU --
YOLOv10-Detection float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 3.703 ms 0 - 100 MB NPU --
YOLOv10-Detection float SA8775P ADP Qualcomm® SA8775P TFLITE 5.09 ms 0 - 70 MB NPU --
YOLOv10-Detection float SA8775P ADP Qualcomm® SA8775P QNN_DLC 5.162 ms 2 - 101 MB NPU --
YOLOv10-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 2.754 ms 8 - 96 MB NPU --
YOLOv10-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 2.686 ms 5 - 237 MB NPU --
YOLOv10-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 3.812 ms 0 - 195 MB NPU --
YOLOv10-Detection float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 2.078 ms 0 - 77 MB NPU --
YOLOv10-Detection float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 2.044 ms 5 - 104 MB NPU --
YOLOv10-Detection float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 3.615 ms 1 - 92 MB NPU --
YOLOv10-Detection float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 1.74 ms 0 - 70 MB NPU --
YOLOv10-Detection float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 1.588 ms 5 - 123 MB NPU --
YOLOv10-Detection float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 2.616 ms 3 - 91 MB NPU --
YOLOv10-Detection float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 4.092 ms 152 - 152 MB NPU --
YOLOv10-Detection float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 6.397 ms 5 - 5 MB NPU --
YOLOv10-Detection w8a16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 7.06 ms 2 - 37 MB NPU --
YOLOv10-Detection w8a16 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 4.637 ms 2 - 45 MB NPU --
YOLOv10-Detection w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 3.759 ms 2 - 13 MB NPU --
YOLOv10-Detection w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 54.208 ms 9 - 198 MB NPU --
YOLOv10-Detection w8a16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 4.405 ms 2 - 37 MB NPU --
YOLOv10-Detection w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_DLC 11.841 ms 2 - 38 MB NPU --
YOLOv10-Detection w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) ONNX 171.128 ms 73 - 89 MB CPU --
YOLOv10-Detection w8a16 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) ONNX 140.736 ms 69 - 74 MB CPU --
YOLOv10-Detection w8a16 SA7255P ADP Qualcomm® SA7255P QNN_DLC 7.06 ms 2 - 37 MB NPU --
YOLOv10-Detection w8a16 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 3.759 ms 0 - 11 MB NPU --
YOLOv10-Detection w8a16 SA8295P ADP Qualcomm® SA8295P QNN_DLC 5.013 ms 2 - 41 MB NPU --
YOLOv10-Detection w8a16 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 3.762 ms 2 - 14 MB NPU --
YOLOv10-Detection w8a16 SA8775P ADP Qualcomm® SA8775P QNN_DLC 4.405 ms 2 - 37 MB NPU --
YOLOv10-Detection w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 2.526 ms 2 - 46 MB NPU --
YOLOv10-Detection w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 41.849 ms 0 - 2361 MB NPU --
YOLOv10-Detection w8a16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 1.77 ms 2 - 45 MB NPU --
YOLOv10-Detection w8a16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 38.994 ms 21 - 1065 MB NPU --
YOLOv10-Detection w8a16 Snapdragon 7 Gen 5 QRD Snapdragon® 7 Gen 5 Mobile QNN_DLC 4.323 ms 2 - 44 MB NPU --
YOLOv10-Detection w8a16 Snapdragon 7 Gen 5 QRD Snapdragon® 7 Gen 5 Mobile ONNX 157.644 ms 91 - 110 MB CPU --
YOLOv10-Detection w8a16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 1.484 ms 2 - 40 MB NPU --
YOLOv10-Detection w8a16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 36.224 ms 7 - 939 MB NPU --
YOLOv10-Detection w8a16 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 4.226 ms 4 - 4 MB NPU --
YOLOv10-Detection w8a16 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 54.511 ms 29 - 29 MB NPU --
YOLOv10-Detection w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 3.512 ms 0 - 26 MB NPU --
YOLOv10-Detection w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 3.432 ms 1 - 27 MB NPU --
YOLOv10-Detection w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 1.915 ms 0 - 36 MB NPU --
YOLOv10-Detection w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 1.905 ms 1 - 35 MB NPU --
YOLOv10-Detection w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 1.718 ms 0 - 13 MB NPU --
YOLOv10-Detection w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 1.652 ms 1 - 14 MB NPU --
YOLOv10-Detection w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 3.758 ms 0 - 28 MB NPU --
YOLOv10-Detection w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 2.183 ms 0 - 26 MB NPU --
YOLOv10-Detection w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 2.067 ms 1 - 28 MB NPU --
YOLOv10-Detection w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 4.141 ms 0 - 33 MB NPU --
YOLOv10-Detection w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_DLC 4.945 ms 1 - 36 MB NPU --
YOLOv10-Detection w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) ONNX 43.318 ms 22 - 39 MB CPU --
YOLOv10-Detection w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 50.064 ms 2 - 9 MB NPU --
YOLOv10-Detection w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) ONNX 39.376 ms 21 - 26 MB CPU --
YOLOv10-Detection w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 3.512 ms 0 - 26 MB NPU --
YOLOv10-Detection w8a8 SA7255P ADP Qualcomm® SA7255P QNN_DLC 3.432 ms 1 - 27 MB NPU --
YOLOv10-Detection w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 1.735 ms 0 - 14 MB NPU --
YOLOv10-Detection w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 1.658 ms 1 - 12 MB NPU --
YOLOv10-Detection w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 2.608 ms 0 - 32 MB NPU --
YOLOv10-Detection w8a8 SA8295P ADP Qualcomm® SA8295P QNN_DLC 2.477 ms 0 - 32 MB NPU --
YOLOv10-Detection w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 1.728 ms 0 - 13 MB NPU --
YOLOv10-Detection w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 1.661 ms 0 - 13 MB NPU --
YOLOv10-Detection w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 2.183 ms 0 - 26 MB NPU --
YOLOv10-Detection w8a8 SA8775P ADP Qualcomm® SA8775P QNN_DLC 2.067 ms 1 - 28 MB NPU --
YOLOv10-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 1.146 ms 0 - 36 MB NPU --
YOLOv10-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 1.135 ms 1 - 33 MB NPU --
YOLOv10-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 2.643 ms 0 - 81 MB NPU --
YOLOv10-Detection w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 0.865 ms 0 - 28 MB NPU --
YOLOv10-Detection w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 0.814 ms 1 - 30 MB NPU --
YOLOv10-Detection w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 2.105 ms 0 - 55 MB NPU --
YOLOv10-Detection w8a8 Snapdragon 7 Gen 5 QRD Snapdragon® 7 Gen 5 Mobile TFLITE 1.915 ms 0 - 33 MB NPU --
YOLOv10-Detection w8a8 Snapdragon 7 Gen 5 QRD Snapdragon® 7 Gen 5 Mobile QNN_DLC 1.761 ms 1 - 37 MB NPU --
YOLOv10-Detection w8a8 Snapdragon 7 Gen 5 QRD Snapdragon® 7 Gen 5 Mobile ONNX 38.223 ms 23 - 41 MB CPU --
YOLOv10-Detection w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 0.836 ms 0 - 29 MB NPU --
YOLOv10-Detection w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 0.765 ms 1 - 33 MB NPU --
YOLOv10-Detection w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 1.98 ms 0 - 81 MB NPU --
YOLOv10-Detection w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 1.906 ms 1 - 1 MB NPU --
YOLOv10-Detection w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 3.866 ms 1 - 1 MB NPU --
YOLOv10-Detection w8a8_mixed_int16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 2.436 ms 2 - 13 MB NPU --
YOLOv10-Detection w8a8_mixed_int16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 59.444 ms 19 - 177 MB NPU --
YOLOv10-Detection w8a8_mixed_int16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 3.023 ms 1 - 29 MB NPU --
YOLOv10-Detection w8a8_mixed_int16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) ONNX 133.33 ms 56 - 72 MB CPU --
YOLOv10-Detection w8a8_mixed_int16 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) ONNX 123.823 ms 54 - 61 MB CPU --
YOLOv10-Detection w8a8_mixed_int16 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 2.451 ms 2 - 12 MB NPU --
YOLOv10-Detection w8a8_mixed_int16 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 2.447 ms 2 - 12 MB NPU --
YOLOv10-Detection w8a8_mixed_int16 SA8775P ADP Qualcomm® SA8775P QNN_DLC 3.023 ms 1 - 29 MB NPU --
YOLOv10-Detection w8a8_mixed_int16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 1.634 ms 2 - 39 MB NPU --
YOLOv10-Detection w8a8_mixed_int16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 43.294 ms 2 - 2325 MB NPU --
YOLOv10-Detection w8a8_mixed_int16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 1.203 ms 2 - 37 MB NPU --
YOLOv10-Detection w8a8_mixed_int16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 38.672 ms 20 - 964 MB NPU --
YOLOv10-Detection w8a8_mixed_int16 Snapdragon 7 Gen 5 QRD Snapdragon® 7 Gen 5 Mobile QNN_DLC 2.761 ms 2 - 39 MB NPU --
YOLOv10-Detection w8a8_mixed_int16 Snapdragon 7 Gen 5 QRD Snapdragon® 7 Gen 5 Mobile ONNX 128.434 ms 60 - 79 MB CPU --
YOLOv10-Detection w8a8_mixed_int16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 1.027 ms 2 - 37 MB NPU --
YOLOv10-Detection w8a8_mixed_int16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 39.524 ms 7 - 949 MB NPU --
YOLOv10-Detection w8a8_mixed_int16 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 2.745 ms 2 - 2 MB NPU --
YOLOv10-Detection w8a8_mixed_int16 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 53.975 ms 26 - 26 MB NPU --

Installation

Install the package via pip:

pip install "qai-hub-models[yolov10-det]"

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

Sign-in to Qualcomm® AI Hub 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.

qai-hub configure --api_token API_TOKEN

Navigate to 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.

python -m qai_hub_models.models.yolov10_det.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.yolov10_det.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.
python -m qai_hub_models.models.yolov10_det.export

How does this work?

This export script leverages Qualcomm® AI Hub 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.

import torch

import qai_hub as hub
from qai_hub_models.models.yolov10_det 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.

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.

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. Sign up for access.

Run demo on a cloud-hosted device

You can also run the demo on-device.

python -m qai_hub_models.models.yolov10_det.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.yolov10_det.demo -- --eval-mode on-device

Deploying compiled model to Android

The models can be deployed using multiple runtimes:

  • TensorFlow Lite (.tflite export): This tutorial provides a guide to deploy the .tflite model in an Android application.

  • QNN (.so export ): This sample app provides instructions on how to use the .so shared library in an Android application.

View on Qualcomm® AI Hub

Get more details on YOLOv10-Detection's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of YOLOv10-Detection can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Downloads last month

-

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