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 1.24.3 | Download |
| QNN_DLC | float | Universal | QAIRT 2.43 | Download |
| TFLITE | float | Universal | QAIRT 2.43, TFLite 2.19.1 | 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 | 3.876 ms | 0 - 416 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® X2 Elite | 3.567 ms | 263 - 263 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® X Elite | 8.525 ms | 263 - 263 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.566 ms | 0 - 451 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® QCS8550 (Proxy) | 7.955 ms | 0 - 323 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Qualcomm® QCS9075 | 10.796 ms | 0 - 3 MB | NPU |
| Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.34 ms | 0 - 419 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.893 ms | 0 - 411 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® X2 Elite | 3.99 ms | 1 - 1 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® X Elite | 8.042 ms | 0 - 0 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.275 ms | 0 - 447 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 28.364 ms | 0 - 416 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 7.478 ms | 0 - 2 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA8775P | 9.669 ms | 0 - 415 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS9075 | 10.458 ms | 0 - 2 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 11.013 ms | 0 - 427 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA7255P | 28.364 ms | 0 - 416 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA8295P | 10.587 ms | 0 - 396 MB | NPU |
| Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.287 ms | 0 - 413 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.879 ms | 0 - 418 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.3 ms | 0 - 452 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 28.339 ms | 0 - 419 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 7.322 ms | 0 - 3 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8775P | 9.721 ms | 0 - 419 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS9075 | 10.575 ms | 0 - 265 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 10.949 ms | 0 - 428 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA7255P | 28.339 ms | 0 - 419 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8295P | 10.639 ms | 0 - 397 MB | NPU |
| Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.364 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.