Albert-Base-V2-Hf: Optimized for Qualcomm Devices

ALBERT 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 Albert-Base-V2-Hf 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
QNN_DLC	float	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit Albert-Base-V2-Hf 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 Albert-Base-V2-Hf on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

• Model checkpoint: albert/albert-base-v2
• Input resolution: 1x384
• Number of parameters: 11.8M
• Model size (float): 43.9 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® X2 Elite	9.271 ms	0 - 0 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® X Elite	21.017 ms	1 - 1 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	16.82 ms	0 - 355 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	33.851 ms	0 - 422 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8275	72.477 ms	0 - 307 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	21.22 ms	0 - 2 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® SA8775P	25.893 ms	0 - 307 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® SA8650P	25.893 ms	0 - 307 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® SA8255P	25.893 ms	0 - 307 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® QCS8450	33.851 ms	0 - 422 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	28.445 ms	0 - 2 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	21.017 ms	1 - 1 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	11.112 ms	0 - 398 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® SA7255P	72.477 ms	0 - 307 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® SA8295P	31.27 ms	0 - 377 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® 8 Elite Mobile	11.112 ms	0 - 398 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	8.192 ms	0 - 398 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	16.757 ms	0 - 364 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	34.319 ms	0 - 425 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® Dragonwing™ QCS8275	73.091 ms	0 - 323 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	21.85 ms	0 - 3 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® SA8775P	26.255 ms	0 - 322 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® SA8650P	26.255 ms	0 - 322 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® SA8255P	26.255 ms	0 - 322 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® QCS8450	34.319 ms	0 - 425 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	25.621 ms	0 - 32 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	11.363 ms	0 - 392 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® SA7255P	73.091 ms	0 - 323 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® SA8295P	31.317 ms	0 - 376 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Snapdragon® 8 Elite Mobile	11.363 ms	0 - 392 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	8.953 ms	0 - 326 MB	NPU

License

• The license for the original implementation of Albert-Base-V2-Hf can be found here.

References

• ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
• 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.