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 2.37, ONNX Runtime 1.23.0	Download
QNN_DLC	float	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 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® X Elite	22.459 ms	294 - 294 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® 8 Gen 3 Mobile	15.269 ms	0 - 796 MB	NPU
OpenAI-Clip	ONNX	float	Qualcomm® QCS8550 (Proxy)	22.212 ms	0 - 323 MB	NPU
OpenAI-Clip	ONNX	float	Qualcomm® QCS9075	25.758 ms	0 - 4 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	12.318 ms	1 - 713 MB	NPU
OpenAI-Clip	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	10.095 ms	1 - 661 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® X Elite	18.808 ms	1 - 1 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	12.624 ms	0 - 550 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	55.883 ms	1 - 507 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	17.922 ms	1 - 593 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® SA8775P	20.876 ms	1 - 504 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® QCS9075	20.902 ms	1 - 3 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	21.094 ms	0 - 501 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® SA7255P	55.883 ms	1 - 507 MB	NPU
OpenAI-Clip	QNN_DLC	float	Qualcomm® SA8295P	22.195 ms	0 - 492 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	10.588 ms	1 - 515 MB	NPU
OpenAI-Clip	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	8.462 ms	0 - 485 MB	NPU
OpenAI-Clip	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	11.008 ms	0 - 562 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® QCS8275 (Proxy)	52.168 ms	0 - 512 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® QCS8550 (Proxy)	15.689 ms	0 - 4 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® SA8775P	18.638 ms	0 - 509 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® QCS9075	20.357 ms	0 - 294 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® QCS8450 (Proxy)	20.361 ms	0 - 503 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® SA7255P	52.168 ms	0 - 512 MB	NPU
OpenAI-Clip	TFLITE	float	Qualcomm® SA8295P	21.567 ms	0 - 495 MB	NPU
OpenAI-Clip	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	9.059 ms	0 - 526 MB	NPU
OpenAI-Clip	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	7.023 ms	0 - 497 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.