Hugging Face's logo

qualcomm
/
YOLOv11-Detection

Object Detection
PyTorch
real_time
android
Model card Files
xet
Community

YOLOv11-Detection: Optimized for Mobile Deployment

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

Ultralytics YOLOv11 is a machine learning model that predicts bounding boxes and classes of objects in an image.

This model is an implementation of YOLOv11-Detection found here.

This repository provides scripts to run YOLOv11-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: YOLO11-N
    • Input resolution: 640x640
    • Number of parameters: 2.64M
    • Model size (float): 10.1 MB
    • Model size (w8a8): 2.83 MB
    • Model size (w8a16): 3.30 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
YOLOv11-Detection float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 12.833 ms 0 - 80 MB NPU --
YOLOv11-Detection float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 12.21 ms 0 - 98 MB NPU --
YOLOv11-Detection float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 6.983 ms 0 - 43 MB NPU --
YOLOv11-Detection float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 7.689 ms 5 - 42 MB NPU --
YOLOv11-Detection float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 3.868 ms 0 - 74 MB NPU --
YOLOv11-Detection float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 3.652 ms 5 - 79 MB NPU --
YOLOv11-Detection float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 5.441 ms 1 - 54 MB NPU --
YOLOv11-Detection float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 21.166 ms 0 - 80 MB NPU --
YOLOv11-Detection float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 5.107 ms 2 - 99 MB NPU --
YOLOv11-Detection float SA7255P ADP Qualcomm® SA7255P TFLITE 12.833 ms 0 - 80 MB NPU --
YOLOv11-Detection float SA7255P ADP Qualcomm® SA7255P QNN_DLC 12.21 ms 0 - 98 MB NPU --
YOLOv11-Detection float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 3.868 ms 0 - 75 MB NPU --
YOLOv11-Detection float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 3.646 ms 4 - 79 MB NPU --
YOLOv11-Detection float SA8295P ADP Qualcomm® SA8295P TFLITE 8.18 ms 0 - 34 MB NPU --
YOLOv11-Detection float SA8295P ADP Qualcomm® SA8295P QNN_DLC 8.167 ms 0 - 39 MB NPU --
YOLOv11-Detection float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 3.868 ms 0 - 80 MB NPU --
YOLOv11-Detection float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 3.659 ms 2 - 83 MB NPU --
YOLOv11-Detection float SA8775P ADP Qualcomm® SA8775P TFLITE 21.166 ms 0 - 80 MB NPU --
YOLOv11-Detection float SA8775P ADP Qualcomm® SA8775P QNN_DLC 5.107 ms 2 - 99 MB NPU --
YOLOv11-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 2.784 ms 0 - 150 MB NPU --
YOLOv11-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 2.642 ms 0 - 231 MB NPU --
YOLOv11-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 3.707 ms 3 - 106 MB NPU --
YOLOv11-Detection float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 2.193 ms 0 - 90 MB NPU --
YOLOv11-Detection float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 2.12 ms 5 - 105 MB NPU --
YOLOv11-Detection float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 3.598 ms 2 - 88 MB NPU --
YOLOv11-Detection float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 1.755 ms 0 - 85 MB NPU --
YOLOv11-Detection float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 1.587 ms 5 - 125 MB NPU --
YOLOv11-Detection float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 2.693 ms 3 - 68 MB NPU --
YOLOv11-Detection float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 4.081 ms 137 - 137 MB NPU --
YOLOv11-Detection float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 5.75 ms 5 - 5 MB NPU --
YOLOv11-Detection w8a16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 7.69 ms 1 - 33 MB NPU --
YOLOv11-Detection w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 4.248 ms 2 - 12 MB NPU --
YOLOv11-Detection w8a16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 4.872 ms 0 - 32 MB NPU --
YOLOv11-Detection w8a16 SA7255P ADP Qualcomm® SA7255P QNN_DLC 7.69 ms 1 - 33 MB NPU --
YOLOv11-Detection w8a16 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 4.248 ms 2 - 13 MB NPU --
YOLOv11-Detection w8a16 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 4.24 ms 2 - 12 MB NPU --
YOLOv11-Detection w8a16 SA8775P ADP Qualcomm® SA8775P QNN_DLC 4.872 ms 0 - 32 MB NPU --
YOLOv11-Detection w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 2.91 ms 2 - 51 MB NPU --
YOLOv11-Detection w8a16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 2.122 ms 2 - 44 MB NPU --
YOLOv11-Detection w8a16 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile QNN_DLC 4.469 ms 2 - 43 MB NPU --
YOLOv11-Detection w8a16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 1.849 ms 2 - 48 MB NPU --
YOLOv11-Detection w8a16 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 4.561 ms 0 - 0 MB NPU --
YOLOv11-Detection w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 3.352 ms 1 - 28 MB NPU --
YOLOv11-Detection w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 1.904 ms 0 - 36 MB NPU --
YOLOv11-Detection w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 1.852 ms 1 - 36 MB NPU --
YOLOv11-Detection w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 1.739 ms 0 - 13 MB NPU --
YOLOv11-Detection w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 1.595 ms 1 - 15 MB NPU --
YOLOv11-Detection w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 2.217 ms 0 - 27 MB NPU --
YOLOv11-Detection w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 2.028 ms 1 - 28 MB NPU --
YOLOv11-Detection w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 4.14 ms 0 - 38 MB NPU --
YOLOv11-Detection w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_DLC 5.678 ms 1 - 38 MB NPU --
YOLOv11-Detection w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 66.432 ms 2 - 13 MB NPU --
YOLOv11-Detection w8a8 SA7255P ADP Qualcomm® SA7255P QNN_DLC 3.352 ms 1 - 28 MB NPU --
YOLOv11-Detection w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 1.733 ms 0 - 13 MB NPU --
YOLOv11-Detection w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 1.602 ms 0 - 13 MB NPU --
YOLOv11-Detection w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 2.611 ms 0 - 32 MB NPU --
YOLOv11-Detection w8a8 SA8295P ADP Qualcomm® SA8295P QNN_DLC 2.417 ms 1 - 35 MB NPU --
YOLOv11-Detection w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 1.743 ms 0 - 13 MB NPU --
YOLOv11-Detection w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 1.596 ms 1 - 14 MB NPU --
YOLOv11-Detection w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 2.217 ms 0 - 27 MB NPU --
YOLOv11-Detection w8a8 SA8775P ADP Qualcomm® SA8775P QNN_DLC 2.028 ms 1 - 28 MB NPU --
YOLOv11-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 1.153 ms 0 - 37 MB NPU --
YOLOv11-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 1.072 ms 1 - 42 MB NPU --
YOLOv11-Detection w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 0.877 ms 0 - 30 MB NPU --
YOLOv11-Detection w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 0.795 ms 1 - 32 MB NPU --
YOLOv11-Detection w8a8 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile TFLITE 1.956 ms 0 - 34 MB NPU --
YOLOv11-Detection w8a8 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile QNN_DLC 1.722 ms 1 - 37 MB NPU --
YOLOv11-Detection w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 0.833 ms 0 - 36 MB NPU --
YOLOv11-Detection w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 0.735 ms 1 - 38 MB NPU --
YOLOv11-Detection w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 1.872 ms 1 - 1 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 6.046 ms 1 - 32 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 3.205 ms 2 - 12 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 3.804 ms 1 - 32 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 SA7255P ADP Qualcomm® SA7255P QNN_DLC 6.046 ms 1 - 32 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 3.22 ms 2 - 12 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 3.206 ms 2 - 12 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 SA8775P ADP Qualcomm® SA8775P QNN_DLC 3.804 ms 1 - 32 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 2.271 ms 2 - 47 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 1.7 ms 2 - 37 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile QNN_DLC 3.15 ms 2 - 38 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 1.516 ms 2 - 44 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 3.478 ms 1 - 1 MB NPU --

Installation

Install the package via pip:

# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
pip install "qai-hub-models[yolov11-det]"

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

Sign-in to Qualcomm® AI Hub Workbench 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.yolov11_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.yolov11_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.yolov11_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.yolov11_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 Workbench. 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.yolov11_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.yolov11_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 YOLOv11-Detection's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of YOLOv11-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