Hugging Face's logo

qualcomm
/
MiniLM-v2

Text Generation
PyTorch
foundation
real_time
android
Model card Files
xet
 Community

MiniLM-v2: Optimized for Qualcomm Devices

All-MiniLM-L6-v2 maps sentences to a 384-dimensional dense vector space. Trained on 1B+ sentence pairs, it excels at semantic search, clustering, and sentence similarity tasks while being small enough to run on mobile devices.

This is based on the implementation of MiniLM-v2 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 1.27.1 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a8 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download
TFLITE w8a8 Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit MiniLM-v2 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 MiniLM-v2 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

  • Embedding dimension: 384
  • Input resolution: 128 tokens
  • Model checkpoint: sentence-transformers/all-MiniLM-L6-v2
  • Model size (float): 86.7 MB
  • Number of parameters: 22.7M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
MiniLM-v2 ONNX float Snapdragon® X2 Elite 0.671 ms 1 - 1 MB NPU
MiniLM-v2 ONNX float Snapdragon® X Elite 1.673 ms 44 - 44 MB NPU
MiniLM-v2 ONNX float Snapdragon® 8 Gen 3 Mobile 1.128 ms 0 - 102 MB NPU
MiniLM-v2 ONNX float Snapdragon® 8 Gen 1 Mobile 2.35 ms 0 - 107 MB NPU
MiniLM-v2 ONNX float Qualcomm® Dragonwing™ IQ-8275 1.785 ms 0 - 4 MB NPU
MiniLM-v2 ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.621 ms 0 - 50 MB NPU
MiniLM-v2 ONNX float Qualcomm® QCS8450 2.35 ms 0 - 107 MB NPU
MiniLM-v2 ONNX float Qualcomm® Dragonwing™ IQ-9075 2.004 ms 0 - 3 MB NPU
MiniLM-v2 ONNX float Qualcomm® Dragonwing™ IQ-X7181 1.673 ms 44 - 44 MB NPU
MiniLM-v2 ONNX float Qualcomm® Dragonwing™ Q-8750 0.789 ms 0 - 60 MB NPU
MiniLM-v2 ONNX float Snapdragon® 8 Elite Mobile 0.789 ms 0 - 60 MB NPU
MiniLM-v2 ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.643 ms 0 - 62 MB NPU
MiniLM-v2 ONNX w8a8 Snapdragon® X2 Elite 0.671 ms 1 - 1 MB NPU
MiniLM-v2 ONNX w8a8 Snapdragon® X Elite 1.782 ms 23 - 23 MB NPU
MiniLM-v2 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 1.207 ms 0 - 87 MB NPU
MiniLM-v2 ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 1.964 ms 0 - 87 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 5.267 ms 0 - 3 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 1.673 ms 0 - 4 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.707 ms 0 - 26 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® QCS8450 1.964 ms 0 - 87 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 1.797 ms 0 - 3 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.782 ms 23 - 23 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 6.704 ms 0 - 60 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 1.953 ms 0 - 54 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.843 ms 0 - 60 MB NPU
MiniLM-v2 ONNX w8a8 Snapdragon® 8 Elite Mobile 0.843 ms 0 - 60 MB NPU
MiniLM-v2 ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.665 ms 0 - 57 MB NPU
MiniLM-v2 ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 1.953 ms 0 - 54 MB NPU
MiniLM-v2 QNN_DLC float Snapdragon® X2 Elite 0.677 ms 1 - 1 MB NPU
MiniLM-v2 QNN_DLC float Snapdragon® X Elite 1.288 ms 1 - 1 MB NPU
MiniLM-v2 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.788 ms 0 - 99 MB NPU
MiniLM-v2 QNN_DLC float Snapdragon® 8 Gen 1 Mobile 1.895 ms 0 - 101 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 1.323 ms 0 - 2 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 3.572 ms 0 - 58 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.115 ms 0 - 7 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® SA8775P 1.521 ms 0 - 60 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® SA8650P 1.521 ms 0 - 60 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® SA8255P 1.521 ms 0 - 60 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® QCS8450 1.895 ms 0 - 101 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.39 ms 2 - 4 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.288 ms 1 - 1 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.565 ms 0 - 59 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® SA7255P 3.572 ms 0 - 58 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® SA8295P 2.286 ms 0 - 57 MB NPU
MiniLM-v2 QNN_DLC float Snapdragon® 8 Elite Mobile 0.565 ms 0 - 59 MB NPU
MiniLM-v2 QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.464 ms 0 - 61 MB NPU
MiniLM-v2 QNN_DLC w8a8 Snapdragon® X2 Elite 0.815 ms 1 - 1 MB NPU
MiniLM-v2 QNN_DLC w8a8 Snapdragon® X Elite 1.909 ms 1 - 1 MB NPU
MiniLM-v2 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 1.208 ms 0 - 73 MB NPU
MiniLM-v2 QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 1.954 ms 0 - 72 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 4.003 ms 2 - 4 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 1.647 ms 0 - 2 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 3.449 ms 0 - 48 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.717 ms 0 - 2 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® SA8775P 1.931 ms 0 - 50 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® SA8650P 1.931 ms 0 - 50 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® SA8255P 1.931 ms 0 - 50 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® QCS8450 1.954 ms 0 - 72 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 1.994 ms 0 - 2 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.909 ms 1 - 1 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 6.135 ms 0 - 50 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 1.699 ms 0 - 47 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.833 ms 0 - 48 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® SA7255P 3.449 ms 0 - 48 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® SA8295P 2.371 ms 0 - 46 MB NPU
MiniLM-v2 QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.833 ms 0 - 48 MB NPU
MiniLM-v2 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.671 ms 0 - 51 MB NPU
MiniLM-v2 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.699 ms 0 - 47 MB NPU
MiniLM-v2 TFLITE float Snapdragon® 8 Gen 3 Mobile 0.829 ms 0 - 103 MB NPU
MiniLM-v2 TFLITE float Snapdragon® 8 Gen 1 Mobile 1.96 ms 0 - 104 MB NPU
MiniLM-v2 TFLITE float Qualcomm® Dragonwing™ IQ-8275 1.383 ms 0 - 46 MB NPU
MiniLM-v2 TFLITE float Qualcomm® Dragonwing™ IQ-8275 3.674 ms 0 - 63 MB NPU
MiniLM-v2 TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.132 ms 0 - 6 MB NPU
MiniLM-v2 TFLITE float Qualcomm® SA8775P 1.556 ms 0 - 65 MB NPU
MiniLM-v2 TFLITE float Qualcomm® SA8650P 1.556 ms 0 - 65 MB NPU
MiniLM-v2 TFLITE float Qualcomm® SA8255P 1.556 ms 0 - 65 MB NPU
MiniLM-v2 TFLITE float Qualcomm® QCS8450 1.96 ms 0 - 104 MB NPU
MiniLM-v2 TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.402 ms 0 - 45 MB NPU
MiniLM-v2 TFLITE float Qualcomm® Dragonwing™ Q-8750 0.593 ms 0 - 58 MB NPU
MiniLM-v2 TFLITE float Qualcomm® SA7255P 3.674 ms 0 - 63 MB NPU
MiniLM-v2 TFLITE float Qualcomm® SA8295P 2.375 ms 0 - 56 MB NPU
MiniLM-v2 TFLITE float Snapdragon® 8 Elite Mobile 0.593 ms 0 - 58 MB NPU
MiniLM-v2 TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.485 ms 0 - 58 MB NPU
MiniLM-v2 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 1.666 ms 0 - 82 MB NPU
MiniLM-v2 TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 2.604 ms 0 - 79 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 15.688 ms 0 - 31 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 2.268 ms 0 - 25 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 4.64 ms 0 - 55 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.376 ms 0 - 2 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® SA8775P 2.681 ms 0 - 59 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® SA8650P 2.681 ms 0 - 59 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® SA8255P 2.681 ms 0 - 59 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® QCS8450 2.604 ms 0 - 79 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 2.502 ms 0 - 24 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 12.098 ms 0 - 36 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 5.046 ms 0 - 35 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 1.134 ms 0 - 62 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® SA7255P 4.64 ms 0 - 55 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® SA8295P 3.21 ms 0 - 48 MB NPU
MiniLM-v2 TFLITE w8a8 Snapdragon® 8 Elite Mobile 1.134 ms 0 - 62 MB NPU
MiniLM-v2 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.95 ms 0 - 56 MB NPU
MiniLM-v2 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 5.046 ms 0 - 35 MB NPU

License

  • The license for the original implementation of MiniLM-v2 can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/MiniLM-v2