Mobile-Bert-Uncased-Google: Optimized for Qualcomm Devices

MOBILEBERT is a lightweight BERT model designed for efficient self-supervised learning of language representations. It can be used for masked language modeling and as a backbone for various NLP tasks.

This is based on the implementation of Mobile-Bert-Uncased-Google found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up 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 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit Mobile-Bert-Uncased-Google on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models 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 Mobile-Bert-Uncased-Google on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

• Model checkpoint: mobile_bert_uncased_google
• Input resolution: 1x384
• Number of parameters: 25.3M
• Model size (float): 130 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Mobile-Bert-Uncased-Google	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	13.907 ms	0 - 227 MB	NPU
Mobile-Bert-Uncased-Google	ONNX	float	Snapdragon® 8 Elite Mobile	15.541 ms	0 - 242 MB	NPU
Mobile-Bert-Uncased-Google	ONNX	float	Snapdragon® X2 Elite	14.283 ms	79 - 79 MB	NPU
Mobile-Bert-Uncased-Google	ONNX	float	Snapdragon® X Elite	25.602 ms	79 - 79 MB	NPU
Mobile-Bert-Uncased-Google	ONNX	float	Snapdragon® X Elite	25.602 ms	79 - 79 MB	NPU
Mobile-Bert-Uncased-Google	ONNX	float	Snapdragon® 8 Gen 3 Mobile	19.443 ms	0 - 412 MB	NPU
Mobile-Bert-Uncased-Google	ONNX	float	Qualcomm® QCS8550 (Proxy)	25.331 ms	0 - 91 MB	NPU
Mobile-Bert-Uncased-Google	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	15.541 ms	0 - 242 MB	NPU
Mobile-Bert-Uncased-Google	ONNX	float	Qualcomm® QCS9075	28.146 ms	0 - 3 MB	NPU
Mobile-Bert-Uncased-Google	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	14.114 ms	0 - 213 MB	NPU
Mobile-Bert-Uncased-Google	QNN_DLC	float	Snapdragon® 8 Elite Mobile	15.373 ms	0 - 214 MB	NPU
Mobile-Bert-Uncased-Google	QNN_DLC	float	Snapdragon® X2 Elite	14.612 ms	1 - 1 MB	NPU
Mobile-Bert-Uncased-Google	QNN_DLC	float	Snapdragon® X Elite	25.747 ms	0 - 0 MB	NPU
Mobile-Bert-Uncased-Google	QNN_DLC	float	Snapdragon® X Elite	25.747 ms	0 - 0 MB	NPU
Mobile-Bert-Uncased-Google	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	19.764 ms	0 - 309 MB	NPU
Mobile-Bert-Uncased-Google	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	26.243 ms	0 - 2 MB	NPU
Mobile-Bert-Uncased-Google	QNN_DLC	float	Qualcomm® SA8775P	28.649 ms	0 - 195 MB	NPU
Mobile-Bert-Uncased-Google	QNN_DLC	float	Qualcomm® SA8775P	28.649 ms	0 - 195 MB	NPU
Mobile-Bert-Uncased-Google	QNN_DLC	float	Qualcomm® SA8775P	28.649 ms	0 - 195 MB	NPU
Mobile-Bert-Uncased-Google	QNN_DLC	float	Qualcomm® SA7255P	56.724 ms	0 - 194 MB	NPU
Mobile-Bert-Uncased-Google	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	29.825 ms	0 - 381 MB	NPU
Mobile-Bert-Uncased-Google	QNN_DLC	float	Qualcomm® SA8295P	33.028 ms	0 - 260 MB	NPU
Mobile-Bert-Uncased-Google	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	15.373 ms	0 - 214 MB	NPU
Mobile-Bert-Uncased-Google	QNN_DLC	float	Qualcomm® QCS9075	28.332 ms	0 - 2 MB	NPU
Mobile-Bert-Uncased-Google	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	13.605 ms	0 - 217 MB	NPU
Mobile-Bert-Uncased-Google	TFLITE	float	Snapdragon® 8 Elite Mobile	15.08 ms	0 - 222 MB	NPU
Mobile-Bert-Uncased-Google	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	19.197 ms	0 - 312 MB	NPU
Mobile-Bert-Uncased-Google	TFLITE	float	Qualcomm® QCS8550 (Proxy)	24.852 ms	0 - 3 MB	NPU
Mobile-Bert-Uncased-Google	TFLITE	float	Qualcomm® SA8775P	27.791 ms	0 - 200 MB	NPU
Mobile-Bert-Uncased-Google	TFLITE	float	Qualcomm® SA8775P	27.791 ms	0 - 200 MB	NPU
Mobile-Bert-Uncased-Google	TFLITE	float	Qualcomm® SA8775P	27.791 ms	0 - 200 MB	NPU
Mobile-Bert-Uncased-Google	TFLITE	float	Qualcomm® SA7255P	55.241 ms	0 - 200 MB	NPU
Mobile-Bert-Uncased-Google	TFLITE	float	Qualcomm® QCS8450 (Proxy)	44.546 ms	0 - 359 MB	NPU
Mobile-Bert-Uncased-Google	TFLITE	float	Qualcomm® SA8295P	32.398 ms	0 - 252 MB	NPU
Mobile-Bert-Uncased-Google	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	15.08 ms	0 - 222 MB	NPU
Mobile-Bert-Uncased-Google	TFLITE	float	Qualcomm® QCS9075	27.864 ms	0 - 82 MB	NPU

License

• The license for the original implementation of Mobile-Bert-Uncased-Google can be found here.

References

• MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.