Hugging Face's logo

qualcomm
/
OpusMT-En-Es

Text Generation
PyTorch
foundation
android
Model card Files
xet
 Community

OpusMT-En-Es: Optimized for Qualcomm Devices

OpusMT English to Spanish translation model is a state-of-the-art neural machine translation system designed for translating English text into Spanish. This model is based on the Marian transformer architecture and has been optimized for edge inference by splitting into encoder and decoder components with modified attention mechanisms. It exhibits robust performance for real-world translation tasks, making it highly reliable for practical applications. The model supports input sequences up to 256 tokens and can generate Spanish translations with high accuracy.

This is based on the implementation of OpusMT-En-Es 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
QNN_CONTEXT_BINARY float qualcomm_qcs8450_proxy QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_qcs8550_proxy QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_qcs9075 QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_sa7255p QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_sa8295p QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_sa8775p QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_snapdragon_8_elite_for_galaxy QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_snapdragon_8_elite_gen5 QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_snapdragon_8gen3 QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_snapdragon_x2_elite QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_snapdragon_x_elite QAIRT 2.43 Download

For more device-specific assets and performance metrics, visit OpusMT-En-Es 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 OpusMT-En-Es on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

  • Model checkpoint: Helsinki-NLP/opus-mt-en-es
  • Input resolution: 256 tokens (English text)
  • Max input sequence length: 256 tokens
  • Max output sequence length: 256 tokens
  • Number of parameters (encoder): ~74M
  • Model size (encoder) (float): ~280 MB
  • Number of parameters (decoder): ~74M
  • Model size (decoder) (float): ~280 MB
  • Number of encoder layers: 6
  • Number of decoder layers: 6
  • Attention heads: 8
  • Hidden dimension: 512

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 2.178 ms 0 - 11 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 1.786 ms 160 - 160 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 3.066 ms 160 - 160 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 2.738 ms 13 - 20 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 3.437 ms 12 - 14 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 3.943 ms 12 - 27 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 2.349 ms 0 - 7 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 2.174 ms 1 - 11 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 2.211 ms 12 - 12 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 3.097 ms 12 - 12 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 2.786 ms 12 - 20 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 6.674 ms 12 - 20 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 3.442 ms 12 - 14 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 4.192 ms 12 - 20 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 3.948 ms 12 - 26 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 4.683 ms 12 - 22 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 6.674 ms 12 - 20 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 4.878 ms 10 - 16 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 2.53 ms 0 - 9 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 1.762 ms 0 - 10 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 1.857 ms 107 - 107 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 4.028 ms 107 - 107 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 2.656 ms 0 - 7 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 3.77 ms 0 - 113 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 4.698 ms 15 - 18 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 2.287 ms 0 - 7 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 1.75 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 2.163 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 3.94 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 2.647 ms 0 - 7 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 12.733 ms 0 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 3.644 ms 0 - 1 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 4.749 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 4.574 ms 2 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 5.048 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 12.733 ms 0 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 5.494 ms 0 - 5 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 2.233 ms 0 - 9 MB NPU

License

  • The license for the original implementation of OpusMT-En-Es 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