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 0.672 ms 1 - 1 MB NPU
MiniLM-v2 ONNX float Snapdragon® X Elite 1.676 ms 44 - 44 MB NPU
MiniLM-v2 ONNX float Snapdragon® 8 Gen 3 Mobile 1.126 ms 0 - 104 MB NPU
MiniLM-v2 ONNX float Snapdragon® 8 Gen 1 Mobile 2.357 ms 0 - 107 MB NPU
MiniLM-v2 ONNX float Qualcomm® Dragonwing™ IQ-8275 1.784 ms 0 - 4 MB NPU
MiniLM-v2 ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.615 ms 0 - 50 MB NPU
MiniLM-v2 ONNX float Qualcomm® QCS8450 2.357 ms 0 - 107 MB NPU
MiniLM-v2 ONNX float Qualcomm® Dragonwing™ IQ-9075 2.437 ms 0 - 3 MB NPU
MiniLM-v2 ONNX float Qualcomm® Dragonwing™ IQ-X7181 1.676 ms 44 - 44 MB NPU
MiniLM-v2 ONNX float Qualcomm® Dragonwing™ Q-8750 0.79 ms 0 - 59 MB NPU
MiniLM-v2 ONNX float Snapdragon® 8 Elite Mobile 0.79 ms 0 - 59 MB NPU
MiniLM-v2 ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.643 ms 0 - 61 MB NPU
MiniLM-v2 ONNX w8a8 Snapdragon® X2 Elite 0.672 ms 1 - 1 MB NPU
MiniLM-v2 ONNX w8a8 Snapdragon® X Elite 1.783 ms 23 - 23 MB NPU
MiniLM-v2 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 1.194 ms 0 - 84 MB NPU
MiniLM-v2 ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 1.98 ms 0 - 87 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 5.535 ms 0 - 3 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 1.67 ms 0 - 4 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.715 ms 0 - 26 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® QCS8450 1.98 ms 0 - 87 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 2.062 ms 0 - 3 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.783 ms 23 - 23 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 6.687 ms 0 - 60 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 1.95 ms 0 - 54 MB NPU
MiniLM-v2 ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.839 ms 0 - 58 MB NPU
MiniLM-v2 ONNX w8a8 Snapdragon® 8 Elite Mobile 0.839 ms 0 - 58 MB NPU
MiniLM-v2 ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.662 ms 0 - 60 MB NPU
MiniLM-v2 ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 1.95 ms 0 - 54 MB NPU
MiniLM-v2 QNN_DLC float Snapdragon® X2 Elite 0.65 ms 1 - 1 MB NPU
MiniLM-v2 QNN_DLC float Snapdragon® X Elite 1.303 ms 1 - 1 MB NPU
MiniLM-v2 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.793 ms 0 - 99 MB NPU
MiniLM-v2 QNN_DLC float Snapdragon® 8 Gen 1 Mobile 1.89 ms 0 - 102 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 1.326 ms 0 - 2 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 3.563 ms 0 - 57 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.124 ms 0 - 3 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® SA8775P 1.51 ms 0 - 59 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® SA8650P 1.51 ms 0 - 59 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® SA8255P 1.51 ms 0 - 59 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® QCS8450 1.89 ms 0 - 102 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.47 ms 2 - 4 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.303 ms 1 - 1 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.568 ms 0 - 60 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® SA7255P 3.563 ms 0 - 57 MB NPU
MiniLM-v2 QNN_DLC float Qualcomm® SA8295P 2.281 ms 0 - 57 MB NPU
MiniLM-v2 QNN_DLC float Snapdragon® 8 Elite Mobile 0.568 ms 0 - 60 MB NPU
MiniLM-v2 QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.466 ms 0 - 61 MB NPU
MiniLM-v2 QNN_DLC w8a8 Snapdragon® X2 Elite 0.806 ms 1 - 1 MB NPU
MiniLM-v2 QNN_DLC w8a8 Snapdragon® X Elite 1.909 ms 0 - 0 MB NPU
MiniLM-v2 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 1.205 ms 0 - 74 MB NPU
MiniLM-v2 QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 1.943 ms 0 - 72 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 4.065 ms 0 - 2 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 1.657 ms 0 - 2 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 3.424 ms 0 - 48 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.726 ms 0 - 33 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® SA8775P 1.941 ms 0 - 52 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® SA8650P 1.941 ms 0 - 52 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® SA8255P 1.941 ms 0 - 52 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® QCS8450 1.943 ms 0 - 72 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 1.824 ms 0 - 2 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.909 ms 0 - 0 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 6.133 ms 0 - 50 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 1.69 ms 0 - 47 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.834 ms 0 - 48 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® SA7255P 3.424 ms 0 - 48 MB NPU
MiniLM-v2 QNN_DLC w8a8 Qualcomm® SA8295P 2.382 ms 0 - 46 MB NPU
MiniLM-v2 QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.834 ms 0 - 48 MB NPU
MiniLM-v2 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.68 ms 0 - 52 MB NPU
MiniLM-v2 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.69 ms 0 - 47 MB NPU
MiniLM-v2 TFLITE float Snapdragon® 8 Gen 3 Mobile 0.832 ms 0 - 105 MB NPU
MiniLM-v2 TFLITE float Snapdragon® 8 Gen 1 Mobile 1.952 ms 0 - 101 MB NPU
MiniLM-v2 TFLITE float Qualcomm® Dragonwing™ IQ-8275 1.401 ms 0 - 46 MB NPU
MiniLM-v2 TFLITE float Qualcomm® Dragonwing™ IQ-8275 3.732 ms 0 - 63 MB NPU
MiniLM-v2 TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.127 ms 0 - 2 MB NPU
MiniLM-v2 TFLITE float Qualcomm® SA8775P 1.568 ms 0 - 65 MB NPU
MiniLM-v2 TFLITE float Qualcomm® SA8650P 1.568 ms 0 - 65 MB NPU
MiniLM-v2 TFLITE float Qualcomm® SA8255P 1.568 ms 0 - 65 MB NPU
MiniLM-v2 TFLITE float Qualcomm® QCS8450 1.952 ms 0 - 101 MB NPU
MiniLM-v2 TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.414 ms 0 - 45 MB NPU
MiniLM-v2 TFLITE float Qualcomm® Dragonwing™ Q-8750 0.596 ms 0 - 66 MB NPU
MiniLM-v2 TFLITE float Qualcomm® SA7255P 3.732 ms 0 - 63 MB NPU
MiniLM-v2 TFLITE float Qualcomm® SA8295P 2.362 ms 0 - 56 MB NPU
MiniLM-v2 TFLITE float Snapdragon® 8 Elite Mobile 0.596 ms 0 - 66 MB NPU
MiniLM-v2 TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.488 ms 0 - 60 MB NPU
MiniLM-v2 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 1.668 ms 0 - 83 MB NPU
MiniLM-v2 TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 2.608 ms 0 - 82 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 15.785 ms 0 - 31 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 2.26 ms 0 - 25 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 4.606 ms 0 - 55 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.361 ms 0 - 5 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® SA8775P 2.647 ms 0 - 59 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® SA8650P 2.647 ms 0 - 59 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® SA8255P 2.647 ms 0 - 59 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® QCS8450 2.608 ms 0 - 82 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 2.499 ms 0 - 24 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 12.153 ms 0 - 38 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 5.059 ms 0 - 35 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 1.137 ms 0 - 61 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® SA7255P 4.606 ms 0 - 55 MB NPU
MiniLM-v2 TFLITE w8a8 Qualcomm® SA8295P 3.197 ms 0 - 48 MB NPU
MiniLM-v2 TFLITE w8a8 Snapdragon® 8 Elite Mobile 1.137 ms 0 - 61 MB NPU
MiniLM-v2 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.951 ms 0 - 56 MB NPU
MiniLM-v2 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 5.059 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