YOLOv11m is the medium-sized variant in the 11th-generation YOLO series, offering an excellent trade-off between inference speed and detection accuracy. Compared to YOLOv11s, YOLOv11m features a deeper architecture, wider feature channels, and enhanced contextual modeling, delivering stronger performance in multi-object detection and medium-resolution image scenarios.

It incorporates improved deep residual blocks, cross-scale attention mechanisms, and adaptive receptive field control strategies, significantly boosting accuracy on small or occluded objects. On benchmarks such as COCO and VOC, YOLOv11m achieves high mean Average Precision (mAP) and stable inference performance, making it ideal for use cases like industrial inspection, urban traffic analysis, and smart manufacturing.

YOLOv11m supports deployment on GPUs, NPUs, and AI accelerators, and is fully compatible with ONNX, TensorRT, and OpenVINO frameworks. It serves as a reliable backbone model for general-purpose object detection tasks.

When the user has fine-tuned the source model, the model conversion process must be performed again.

Users can refer to either of the following two methods to complete the model conversion:

• Using AIMO for model conversion: Click Model Conversion Reference in the Performance Reference section on the right to view the conversion steps.

• Using Qualcomm QNN for model conversion: Please refer to the Qualcomm QNN Documentation.

The model performance benchmarks and example code provided by Model Farm are all implemented based on the APLUX AidLite SDK.

For models in .bin format, you can use either of the following two inference engines to run inference on Qualcomm chips:

Inference using APLUX AidLite: please refer to the APLUX AidLite Developer Documentation

Inference using Qualcomm QNN: Please refer to the Qualcomm QNN Documentation

Inference Example Code

The inference example code is implemented using the AidLite SDK.

Click Model & Code to download the model files and the inference code package. The file structure is as follows:

/model_farm_{model_name}_aidlite
    
    |__ models # folder where model files are stored

    |__ python # aidlite python model inference example

    |__ cpp # aidlite cpp model inference example

    |__ README.md