OpenAI-Clip: Optimized for Qualcomm Devices

Contrastive Language-Image Pre-Training (CLIP) uses a ViT like transformer to get visual features and a causal language model to get the text features. Both the text and visual features can then be used for a variety of zero-shot learning tasks.

This is based on the implementation of OpenAI-Clip 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 OpenAI-Clip 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 OpenAI-Clip on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

• Model checkpoint: ViT-B/16
• Image input resolution: 224x224
• Text context length: 77
• Number of parameters: 150M
• Model size (float): 571 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
OpenAI-Clip	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	6.643 ms	1 - 502 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® 8 Elite Mobile	8.728 ms	0 - 506 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® X2 Elite	6.877 ms	291 - 291 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® X Elite	16.667 ms	291 - 291 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® X Elite	16.667 ms	291 - 291 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® 8 Gen 3 Mobile	11.221 ms	1 - 567 MB	NPU
OpenAI-Clip	ONNX	float	Qualcomm® QCS8550 (Proxy)	15.865 ms	0 - 324 MB	NPU
OpenAI-Clip	ONNX	float	Qualcomm® QCS9075	20.607 ms	0 - 4 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	8.728 ms	0 - 506 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	8.956 ms	0 - 416 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® 8 Elite Mobile	11.607 ms	1 - 586 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® X2 Elite	9.872 ms	1 - 1 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® X Elite	21.316 ms	1 - 1 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® X Elite	21.316 ms	1 - 1 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	14.271 ms	0 - 764 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	59.64 ms	1 - 570 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	20.312 ms	1 - 3 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® SA8775P	23.141 ms	1 - 566 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® SA8775P	23.141 ms	1 - 566 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® SA8775P	23.141 ms	1 - 566 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® QCS9075	23.531 ms	1 - 3 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	23.952 ms	0 - 610 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® SA7255P	59.64 ms	1 - 570 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® SA8295P	24.758 ms	1 - 530 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	11.607 ms	1 - 586 MB	NPU
OpenAI-Clip	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	8.993 ms	0 - 430 MB	NPU
OpenAI-Clip	TFLITE	float	Snapdragon® 8 Elite Mobile	11.303 ms	0 - 604 MB	NPU
OpenAI-Clip	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	14.258 ms	0 - 777 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® QCS8275 (Proxy)	59.778 ms	0 - 567 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® QCS8550 (Proxy)	20.242 ms	0 - 3 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® SA8775P	23.183 ms	0 - 564 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® SA8775P	23.183 ms	0 - 564 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® SA8775P	23.183 ms	0 - 564 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® QCS9075	23.957 ms	0 - 296 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® QCS8450 (Proxy)	24.053 ms	0 - 616 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® SA7255P	59.778 ms	0 - 567 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® SA8295P	24.779 ms	0 - 532 MB	NPU
OpenAI-Clip	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	11.303 ms	0 - 604 MB	NPU

License

• The license for the original implementation of OpenAI-Clip can be found here.

References

• Learning Transferable Visual Models From Natural Language Supervision
• 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.