Advanced innovation at your fingertips
Artificial Intelligence
Artificial intelligence at your fingertips
Qualcomm AI Hub, built on top of the Qualcomm AI Stack, is a developer-centric platform designed to simplify and accelerate the on-device AI applications across various use cases.
Streamline on-device AI development.
Optimized translation
Automatic model conversion from PyTorch or ONNX Runtime for efficient on-device deployment with TensorFlow Lite, ONNX Runtime or Qualcomm AI Engine Direct. Resulting in models optimized for on device deployment, specifically on the NPU.
Real devices
Easily deploy models on hosted devices, provisioned within minutes. Run performance profiling and on-device inference with just a few lines of code.
Bring your own data (BYOD) with Amazon SageMaker
You can customize your chosen model using your own dataset and deploy it on your preferred edge device. This solution leverages Amazon SageMaker for model fine-tuning and Qualcomm AI Hub for edge deployments, offering a seamless, end-to-end model development deployment pipeline. This collaboration unlocks new opportunities for model customization and deployment, empowering developers to adapt their AI solutions to specific use cases and datasets.
Qualcomm AI Hub Models.
Run AI/ML models on real devices within minutes and access a comprehensive library using the Qualcomm® AI Hub. All AI models are optimized for deployment on Qualcomm® and Snapdragon® platforms.
Explore a robust AI software portfolio with Qualcomm AI Stack.
Develop once, deploy everywhere
Support popular operating systems across mobile, compute, XR, IoT, auto, and cloud platforms
Optimize for performance and power efficiency
Leverage advanced quantization and compression techniques for trained neural network models
Multiple levels of access
Freedom to choose different APIs to directly access all accelerator cores
Software providing best-in-class AI performance.
Qualcomm® Neural Processing SDK
An all-in-one SDK that supports heterogenous computing, system-level configurations and designed to direct AI workloads to all accelerator cores on our platforms.
Qualcomm® AI Engine Direct SDK
Provides lower-level, highly customizable unified APIs that speeds up AI models on all AI accelerator cores with individual libraries.
AI Model Efficiency Toolkit (AIMET)
Open-source library for optimizing (compressing and quantizing) trained neural network models. Providing features that have been proven to improve run-time performance of deep learning neural network models.
Stay connected
Receive the latest updates, exclusive offers, and valuable insights delivered straight to your inbox.
Qualcomm® Slack
See what’s new in Qualcomm AI Hub and get support from other developers.
The future of AI is hybrid
AI processing must be distributed between the cloud and devices for AI to scale and reach its full potential.
AI Stack forum
Ask questions, discuss AI development topics, get answers from Qualcomm AI engineers and other AI developers.
AI research
To make AI ubiquitous, we are focused on efficient hardware, algorithmic advancements, and software tools.
