Distil-Bert-Base-Uncased-Hf: Optimized for Qualcomm Devices

DistilBERT 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 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 2.37, ONNX Runtime 1.23.0	Download
ONNX	w8a16	Universal	QAIRT 2.37, ONNX Runtime 1.23.0	Download
QNN_DLC	float	Universal	QAIRT 2.42	Download
QNN_DLC	w8a16	Universal	QAIRT 2.42	Download
TFLITE	float	Universal	QAIRT 2.42, TFLite 2.17.0	Download

For more device-specific assets and performance metrics, visit Distil-Bert-Base-Uncased-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 Distil-Bert-Base-Uncased-Hf on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

• Model checkpoint: distil_bert_base_uncased_hf
• Input resolution: 1x384
• Number of parameters: 11.3M
• Model size (float): 43.3 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Distil-Bert-Base-Uncased-Hf	ONNX	float	Snapdragon® X Elite	18.999 ms	179 - 179 MB	NPU
Distil-Bert-Base-Uncased-Hf	ONNX	float	Snapdragon® 8 Gen 3 Mobile	15.081 ms	0 - 469 MB	NPU
Distil-Bert-Base-Uncased-Hf	ONNX	float	Qualcomm® QCS8550 (Proxy)	20.102 ms	0 - 390 MB	NPU
Distil-Bert-Base-Uncased-Hf	ONNX	float	Qualcomm® QCS9075	22.109 ms	0 - 3 MB	NPU
Distil-Bert-Base-Uncased-Hf	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	10.491 ms	0 - 428 MB	NPU
Distil-Bert-Base-Uncased-Hf	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	8.904 ms	0 - 448 MB	NPU
Distil-Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® X Elite	194.493 ms	590 - 590 MB	NPU
Distil-Bert-Base-Uncased-Hf	ONNX	w8a16	Qualcomm® QCS6490	1352.618 ms	182 - 265 MB	CPU
Distil-Bert-Base-Uncased-Hf	ONNX	w8a16	Qualcomm® QCM6690	728.856 ms	350 - 362 MB	CPU
Distil-Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	335.303 ms	331 - 1042 MB	NPU
Distil-Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	710.038 ms	354 - 367 MB	CPU
Distil-Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	329.203 ms	229 - 938 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	float	Snapdragon® X Elite	14.519 ms	0 - 0 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	11.717 ms	0 - 438 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	49.983 ms	0 - 394 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	15.132 ms	0 - 2 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® SA8775P	18.833 ms	0 - 395 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® QCS9075	19.034 ms	0 - 2 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	36.589 ms	0 - 407 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® SA7255P	49.983 ms	0 - 394 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® SA8295P	23.827 ms	0 - 375 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	8.154 ms	0 - 392 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	6.856 ms	0 - 357 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Snapdragon® X Elite	7.907 ms	0 - 0 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	5.106 ms	0 - 357 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	17.698 ms	0 - 290 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	7.395 ms	0 - 2 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® SA8775P	7.589 ms	0 - 290 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® QCS9075	9.247 ms	2 - 4 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® SA7255P	17.698 ms	0 - 290 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	4.094 ms	0 - 290 MB	NPU
Distil-Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	3.012 ms	0 - 309 MB	NPU
Distil-Bert-Base-Uncased-Hf	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	11.806 ms	0 - 450 MB	NPU
Distil-Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® QCS8275 (Proxy)	50.277 ms	0 - 408 MB	NPU
Distil-Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® QCS8550 (Proxy)	14.979 ms	0 - 2 MB	NPU
Distil-Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® SA8775P	19.053 ms	0 - 408 MB	NPU
Distil-Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® QCS9075	19.468 ms	0 - 176 MB	NPU
Distil-Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® QCS8450 (Proxy)	36.783 ms	0 - 417 MB	NPU
Distil-Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® SA7255P	50.277 ms	0 - 408 MB	NPU
Distil-Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® SA8295P	23.484 ms	0 - 387 MB	NPU
Distil-Bert-Base-Uncased-Hf	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	8.482 ms	0 - 398 MB	NPU
Distil-Bert-Base-Uncased-Hf	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	7.099 ms	0 - 378 MB	NPU

License

• The license for the original implementation of Distil-Bert-Base-Uncased-Hf can be found here.

References

• DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

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.