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

Download pre-exported model assets from 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	7.205 ms	291 - 291 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® X Elite	16.481 ms	291 - 291 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® 8 Gen 3 Mobile	11.304 ms	1 - 564 MB	NPU
OpenAI-Clip	ONNX	float	Qualcomm® QCS8550 (Proxy)	15.726 ms	0 - 335 MB	NPU
OpenAI-Clip	ONNX	float	Qualcomm® QCS9075	20.388 ms	0 - 4 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	9.086 ms	1 - 533 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	6.999 ms	1 - 496 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® X2 Elite	9.095 ms	1 - 1 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® X Elite	18.846 ms	1 - 1 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	12.55 ms	0 - 554 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	56.004 ms	1 - 505 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	17.857 ms	1 - 3 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® SA8775P	20.945 ms	1 - 504 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® QCS9075	21.217 ms	3 - 5 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	21.0 ms	0 - 502 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® SA7255P	56.004 ms	1 - 505 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® SA8295P	22.083 ms	1 - 497 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	10.522 ms	1 - 516 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	8.338 ms	0 - 486 MB	NPU
OpenAI-Clip	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	11.082 ms	0 - 559 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® QCS8275 (Proxy)	52.065 ms	0 - 508 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® QCS8550 (Proxy)	15.604 ms	0 - 3 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® SA8775P	18.667 ms	0 - 508 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® QCS9075	20.359 ms	0 - 294 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® QCS8450 (Proxy)	20.309 ms	0 - 502 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® SA7255P	52.065 ms	0 - 508 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® SA8295P	21.252 ms	0 - 495 MB	NPU
OpenAI-Clip	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	9.021 ms	0 - 517 MB	NPU
OpenAI-Clip	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	6.928 ms	0 - 496 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.