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 2.50, ONNX Runtime 1.27.1 | Download |
| QNN_DLC | float | Universal | QAIRT 2.50 | Download |
| TFLITE | float | Universal | QAIRT 2.50 | 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:
- 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® 8 Elite Gen 5 For Galaxy Mobile | 3.837 ms | 0 - 195 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.258 ms | 0 - 185 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® X2 Elite | 3.597 ms | 1 - 1 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® X Elite | 8.296 ms | 263 - 263 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.652 ms | 0 - 399 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 10.97 ms | 0 - 375 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 9.965 ms | 0 - 4 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.899 ms | 0 - 323 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® QCS8450 | 10.97 ms | 0 - 375 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 9.924 ms | 0 - 3 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 8.296 ms | 263 - 263 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.258 ms | 0 - 185 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.87 ms | 0 - 189 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.274 ms | 0 - 179 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® X2 Elite | 3.881 ms | 1 - 1 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® X Elite | 8.581 ms | 0 - 0 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.628 ms | 0 - 394 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 10.876 ms | 0 - 369 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 9.894 ms | 0 - 3 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.955 ms | 0 - 4 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA8775P | 10.141 ms | 0 - 195 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA8650P | 10.141 ms | 0 - 195 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA8255P | 10.141 ms | 0 - 195 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8450 | 10.876 ms | 0 - 369 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 9.863 ms | 0 - 2 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 8.581 ms | 0 - 0 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 4.274 ms | 0 - 179 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA8295P | 11.412 ms | 0 - 176 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.872 ms | 0 - 194 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.294 ms | 0 - 185 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.618 ms | 0 - 396 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 11.06 ms | 0 - 372 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 9.95 ms | 0 - 266 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.899 ms | 0 - 3 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8775P | 10.15 ms | 0 - 199 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8650P | 10.15 ms | 0 - 199 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8255P | 10.15 ms | 0 - 199 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8450 | 11.06 ms | 0 - 372 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 9.889 ms | 0 - 265 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 4.294 ms | 0 - 185 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA7255P | 29.078 ms | 0 - 199 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8295P | 11.417 ms | 0 - 177 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.