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 2.42, ONNX Runtime 1.24.1 | Download |
| QNN_DLC | float | Universal | QAIRT 2.43 | Download |
| TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | Download |
For more device-specific assets and performance metrics, visit Nomic-Embed-Text 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 Nomic-Embed-Text on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.text_generation
Model Stats:
- Model checkpoint: v1.5
- Input resolution: 1x128 (seqlen can vary)
- Number of parameters: 137M
- Model size (float): 523 MB
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.875 ms | 0 - 415 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® X2 Elite | 3.571 ms | 263 - 263 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® X Elite | 8.5 ms | 263 - 263 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.569 ms | 0 - 462 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® QCS8550 (Proxy) | 7.948 ms | 0 - 324 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® QCS9075 | 10.923 ms | 0 - 3 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.335 ms | 0 - 413 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.906 ms | 0 - 413 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® X2 Elite | 3.829 ms | 0 - 0 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® X Elite | 8.004 ms | 0 - 0 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.331 ms | 0 - 446 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 28.373 ms | 0 - 415 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 7.456 ms | 0 - 2 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA8775P | 9.711 ms | 0 - 415 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS9075 | 10.473 ms | 0 - 2 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 11.48 ms | 0 - 430 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA7255P | 28.373 ms | 0 - 415 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA8295P | 10.611 ms | 0 - 396 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.29 ms | 0 - 413 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.874 ms | 0 - 419 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.313 ms | 0 - 453 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 28.33 ms | 0 - 419 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 7.332 ms | 0 - 3 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8775P | 9.682 ms | 0 - 419 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS9075 | 10.634 ms | 0 - 265 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 11.008 ms | 0 - 430 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA7255P | 28.33 ms | 0 - 419 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8295P | 10.642 ms | 0 - 397 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.379 ms | 0 - 422 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.