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
ONNX	float	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a16	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	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	ONNX	float	Snapdragon® X2 Elite	13.117 ms	32 - 32 MB	NPU
Albert-Base-V2-Hf	ONNX	float	Snapdragon® X Elite	26.981 ms	32 - 32 MB	NPU
Albert-Base-V2-Hf	ONNX	float	Snapdragon® 8 Gen 3 Mobile	20.72 ms	0 - 467 MB	NPU
Albert-Base-V2-Hf	ONNX	float	Qualcomm® QCS8550 (Proxy)	26.942 ms	0 - 44 MB	NPU
Albert-Base-V2-Hf	ONNX	float	Qualcomm® QCS9075	30.823 ms	0 - 3 MB	NPU
Albert-Base-V2-Hf	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	15.627 ms	0 - 380 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Snapdragon® X2 Elite	8.632 ms	22 - 22 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Snapdragon® X Elite	19.956 ms	22 - 22 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	14.1 ms	0 - 369 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Qualcomm® QCS6490	2212.365 ms	94 - 121 MB	CPU
Albert-Base-V2-Hf	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	19.184 ms	0 - 29 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Qualcomm® QCS9075	21.413 ms	0 - 3 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Qualcomm® QCM6690	1152.454 ms	80 - 95 MB	CPU
Albert-Base-V2-Hf	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	10.727 ms	0 - 296 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	1110.632 ms	81 - 93 MB	CPU
Albert-Base-V2-Hf	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	8.518 ms	0 - 292 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® X2 Elite	10.606 ms	0 - 0 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® X Elite	22.679 ms	0 - 0 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	17.416 ms	0 - 370 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	75.071 ms	0 - 316 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	23.429 ms	0 - 314 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® SA8775P	27.692 ms	0 - 315 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® QCS9075	26.534 ms	0 - 2 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	52.162 ms	0 - 421 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® SA7255P	75.071 ms	0 - 316 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® SA8295P	34.403 ms	0 - 384 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	11.844 ms	0 - 385 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	9.728 ms	0 - 396 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Snapdragon® X2 Elite	6.21 ms	0 - 0 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Snapdragon® X Elite	13.736 ms	0 - 0 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	9.58 ms	0 - 289 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	29.786 ms	0 - 249 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	13.257 ms	0 - 2 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Qualcomm® SA8775P	13.588 ms	0 - 249 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Qualcomm® QCS9075	15.854 ms	0 - 2 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Qualcomm® SA7255P	29.786 ms	0 - 249 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	7.821 ms	0 - 272 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	5.486 ms	0 - 258 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	17.212 ms	0 - 375 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® QCS8275 (Proxy)	75.008 ms	0 - 331 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® QCS8550 (Proxy)	22.828 ms	0 - 3 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® SA8775P	111.968 ms	0 - 403 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® QCS9075	27.139 ms	0 - 33 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® QCS8450 (Proxy)	51.922 ms	0 - 425 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® SA7255P	75.008 ms	0 - 331 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® SA8295P	34.717 ms	0 - 383 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	12.286 ms	0 - 385 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	9.983 ms	0 - 402 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.