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 1.25.0 | 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.
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 | 3.448 ms | 180 - 180 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® X Elite | 8.23 ms | 264 - 264 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.694 ms | 0 - 388 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 11.498 ms | 0 - 364 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® QCS8550 (Proxy) | 7.931 ms | 0 - 324 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® QCS8450 | 11.498 ms | 0 - 364 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Elite Mobile | 4.292 ms | 0 - 185 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.893 ms | 0 - 191 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® QCS9075 | 10.903 ms | 0 - 45 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® QCS8750 | 4.292 ms | 0 - 185 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® QCS7181 | 8.23 ms | 264 - 264 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® X2 Elite | 3.839 ms | 0 - 0 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® X Elite | 8.455 ms | 1 - 1 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.611 ms | 0 - 421 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 11.776 ms | 0 - 371 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8275 | 29.061 ms | 0 - 198 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 7.917 ms | 0 - 2 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8450 | 11.776 ms | 0 - 371 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 4.375 ms | 0 - 182 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA8295P | 11.544 ms | 0 - 177 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.914 ms | 0 - 190 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA7255P | 29.061 ms | 0 - 198 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS9075 | 10.669 ms | 2 - 4 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8750 | 4.375 ms | 0 - 182 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS7181 | 8.455 ms | 1 - 1 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.586 ms | 0 - 403 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 11.725 ms | 0 - 372 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8275 | 29.073 ms | 0 - 202 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 7.964 ms | 0 - 3 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8775P | 238.535 ms | 8 - 22 MB | CPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8650P | 238.535 ms | 8 - 22 MB | CPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8255P | 238.535 ms | 8 - 22 MB | CPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8450 | 11.725 ms | 0 - 372 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Elite Mobile | 4.375 ms | 0 - 189 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8295P | 11.593 ms | 0 - 179 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.907 ms | 0 - 195 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA7255P | 29.073 ms | 0 - 202 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS9075 | 11.286 ms | 0 - 265 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8750 | 4.375 ms | 0 - 189 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.