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® X2 Elite | 3.572 ms | 263 - 263 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® X Elite | 8.513 ms | 263 - 263 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.576 ms | 0 - 451 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® QCS8550 (Proxy) | 7.941 ms | 0 - 324 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® QCS9075 | 10.976 ms | 0 - 3 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.339 ms | 0 - 413 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.881 ms | 0 - 416 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® X2 Elite | 3.895 ms | 1 - 1 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® X Elite | 8.031 ms | 0 - 0 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.304 ms | 0 - 444 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 28.352 ms | 0 - 415 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 7.455 ms | 0 - 2 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA8775P | 9.687 ms | 0 - 416 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS9075 | 10.47 ms | 0 - 2 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 10.966 ms | 0 - 428 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA7255P | 28.352 ms | 0 - 415 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA8295P | 10.6 ms | 0 - 396 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.419 ms | 0 - 414 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.904 ms | 0 - 412 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.303 ms | 0 - 449 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 28.326 ms | 0 - 419 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 7.47 ms | 0 - 3 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8775P | 9.697 ms | 0 - 419 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS9075 | 10.61 ms | 0 - 265 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 10.912 ms | 0 - 429 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA7255P | 28.326 ms | 0 - 419 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8295P | 10.633 ms | 0 - 398 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.336 ms | 0 - 422 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.879 ms | 0 - 418 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.