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 2.45, ONNX Runtime 1.27.1	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® X2 Elite	10.399 ms	2 - 2 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® X Elite	22.242 ms	294 - 294 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® 8 Gen 3 Mobile	15.078 ms	1 - 1107 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® 8 Gen 1 Mobile	26.71 ms	1 - 685 MB	NPU
OpenAI-Clip	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	21.487 ms	0 - 323 MB	NPU
OpenAI-Clip	ONNX	float	Qualcomm® QCS8450	26.71 ms	1 - 685 MB	NPU
OpenAI-Clip	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	23.85 ms	0 - 4 MB	NPU
OpenAI-Clip	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	22.242 ms	294 - 294 MB	NPU
OpenAI-Clip	ONNX	float	Qualcomm® Dragonwing™ Q-8750	11.707 ms	0 - 869 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® 8 Elite Mobile	11.707 ms	0 - 869 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	9.263 ms	1 - 584 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® X2 Elite	9.634 ms	1 - 1 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® X Elite	21.473 ms	1 - 1 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	14.546 ms	0 - 771 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	24.207 ms	0 - 609 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8275	59.337 ms	1 - 570 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	20.49 ms	1 - 3 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® SA8775P	23.042 ms	1 - 568 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® SA8650P	23.042 ms	1 - 568 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® SA8255P	23.042 ms	1 - 568 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® QCS8450	24.207 ms	0 - 609 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	23.759 ms	1 - 3 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	21.473 ms	1 - 1 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	11.301 ms	1 - 586 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® SA7255P	59.337 ms	1 - 570 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® SA8295P	24.606 ms	1 - 514 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® 8 Elite Mobile	11.301 ms	1 - 586 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	8.754 ms	0 - 420 MB	NPU
OpenAI-Clip	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	14.321 ms	0 - 778 MB	NPU
OpenAI-Clip	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	24.195 ms	0 - 618 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® Dragonwing™ QCS8275	59.391 ms	0 - 565 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	19.987 ms	0 - 3 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® SA8775P	23.117 ms	0 - 566 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® SA8650P	23.117 ms	0 - 566 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® SA8255P	23.117 ms	0 - 566 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® QCS8450	24.195 ms	0 - 618 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	23.088 ms	0 - 296 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	11.502 ms	0 - 598 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® SA7255P	59.391 ms	0 - 565 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® SA8295P	24.505 ms	0 - 517 MB	NPU
OpenAI-Clip	TFLITE	float	Snapdragon® 8 Elite Mobile	11.502 ms	0 - 598 MB	NPU
OpenAI-Clip	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	8.74 ms	0 - 435 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.