Modelpublic

qualcomm/Nomic-Embed-Text

sourceHugging Faceapache-2.0updated 11d agoView on Hugging Face

0likes7downloads

Model Card

Nomic-Embed-Text: Optimized for Qualcomm Devices

A text encoder that surpasses OpenAI text-embedding-ada-002 and text-embedding-3-small performance on short and long context tasks.

This is based on the implementation of Nomic-Embed-Text 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 [Nomic-Embed-Text on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/nomic_embed_text).

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 Nomic-Embed-Text on GitHub for usage instructions.

Model Details

Model Type: Modelusecase.text_generation

Model Stats:

—Input resolution: 1x128 (seqlen can vary)
—Model checkpoint: v1.5
—Model size (float): 523 MB
—Number of parameters: 137M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Nomic-Embed-Text	ONNX	float	Snapdragon® X2 Elite	3.449 ms	1 - 1 MB	NPU
Nomic-Embed-Text	ONNX	float	Snapdragon® X Elite	8.229 ms	263 - 263 MB	NPU
Nomic-Embed-Text	ONNX	float	Snapdragon® 8 Gen 3 Mobile	5.69 ms	0 - 399 MB	NPU
Nomic-Embed-Text	ONNX	float	Snapdragon® 8 Gen 1 Mobile	11.559 ms	0 - 376 MB	NPU
Nomic-Embed-Text	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	9.852 ms	0 - 4 MB	NPU
Nomic-Embed-Text	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	7.953 ms	0 - 322 MB	NPU
Nomic-Embed-Text	ONNX	float	Qualcomm® QCS8450	11.559 ms	0 - 376 MB	NPU
Nomic-Embed-Text	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	9.904 ms	0 - 3 MB	NPU
Nomic-Embed-Text	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	8.229 ms	263 - 263 MB	NPU
Nomic-Embed-Text	ONNX	float	Qualcomm® Dragonwing™ Q-8750	4.325 ms	0 - 187 MB	NPU
Nomic-Embed-Text	ONNX	float	Snapdragon® 8 Elite Mobile	4.325 ms	0 - 187 MB	NPU
Nomic-Embed-Text	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	3.878 ms	0 - 196 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Snapdragon® X2 Elite	3.828 ms	0 - 0 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Snapdragon® X Elite	8.446 ms	0 - 0 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	5.62 ms	0 - 421 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	11.743 ms	0 - 372 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	9.815 ms	0 - 2 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	7.938 ms	0 - 2 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Qualcomm® SA8775P	10.169 ms	0 - 199 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Qualcomm® SA8650P	10.169 ms	0 - 199 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Qualcomm® SA8255P	10.169 ms	0 - 199 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Qualcomm® QCS8450	11.743 ms	0 - 372 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	9.817 ms	2 - 4 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	8.446 ms	0 - 0 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	4.327 ms	0 - 181 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Qualcomm® SA7255P	29.05 ms	0 - 198 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Qualcomm® SA8295P	11.534 ms	0 - 176 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Snapdragon® 8 Elite Mobile	4.327 ms	0 - 181 MB	NPU
Nomic-Embed-Text	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	3.91 ms	0 - 187 MB	NPU
Nomic-Embed-Text	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	5.627 ms	0 - 396 MB	NPU
Nomic-Embed-Text	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	11.756 ms	0 - 370 MB	NPU
Nomic-Embed-Text	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	9.799 ms	0 - 265 MB	NPU
Nomic-Embed-Text	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	7.901 ms	0 - 3 MB	NPU
Nomic-Embed-Text	TFLITE	float	Qualcomm® SA8775P	10.195 ms	0 - 203 MB	NPU
Nomic-Embed-Text	TFLITE	float	Qualcomm® SA8650P	10.195 ms	0 - 203 MB	NPU
Nomic-Embed-Text	TFLITE	float	Qualcomm® SA8255P	10.195 ms	0 - 203 MB	NPU
Nomic-Embed-Text	TFLITE	float	Qualcomm® QCS8450	11.756 ms	0 - 370 MB	NPU
Nomic-Embed-Text	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	9.836 ms	0 - 265 MB	NPU
Nomic-Embed-Text	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	4.35 ms	0 - 189 MB	NPU
Nomic-Embed-Text	TFLITE	float	Qualcomm® SA7255P	29.048 ms	0 - 202 MB	NPU
Nomic-Embed-Text	TFLITE	float	Qualcomm® SA8295P	11.581 ms	0 - 179 MB	NPU
Nomic-Embed-Text	TFLITE	float	Snapdragon® 8 Elite Mobile	4.35 ms	0 - 189 MB	NPU
Nomic-Embed-Text	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	3.914 ms	0 - 197 MB	NPU

License

—The license for the original implementation of Nomic-Embed-Text can be found here.

References

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.