Qualcomm’s AI Hub Expands Support for Snapdragon X Processors, Enabling Developers to Integrate Custom AI Models

With the imminent rise of AI PCs, Qualcomm aims to help developers stay ahead of the curve. The company is launching an update to its AI Hub, now supporting the Snapdragon X processor series. Developers can leverage Qualcomm's latest chips for on-device AI, optimizing their applications for the next generation of Windows computers and laptops.

Additionally, Qualcomm AI Hub is expanding its offerings. Since its launch in February with 75 pre-trained models, the number has now surpassed 100. Going forward, developers won't be limited to Qualcomm's models; they can bring their own.

Are you ready for AI agents? Training models for PCs

Qualcomm’s AI Hub provides developers with a solid starting point for building their applications. Whether you're creating for a smart device, robot, or drone, you'll find suitable models. This also applies to AI-powered mobile app development, which will soon extend to computers. Many popular models are available on Hugging Face and GitHub, all easily deployable on Qualcomm devices, running on CPUs, GPUs, and NPUs using TensorFlow Lite or Qualcomm’s AI Engine Direct.

By supporting the Snapdragon X, Qualcomm positions itself strategically amidst competition from AMD and Intel, who have also announced AI PC processors. Developers can utilize models on Snapdragon X Series Platforms to build AI-powered Windows applications, thanks to integrations with ONNX Runtime, Hugging Face Optimum, and Llama.cpp. This integration may lead to widespread app deployment on computers from brands like Acer, ASUS, Dell, HP, Lenovo, Samsung, and OEM7—many of which are launching PCs powered by Qualcomm's Snapdragon X Elite or X Plus chips.

In collaboration with Andrew Ng’s DeepLearning.ai, Qualcomm is also offering online courses to educate developers about on-device AI and its implementation in their applications.

Bring your own AI

Who knows your customer’s data better than you? While many developers will utilize the over 100 models on Qualcomm’s AI Hub, there will be instances requiring specialized models. Developers can now upload, optimize, and compile SLM and LLMs specifically for Qualcomm and Snapdragon platforms. These models can be quickly tested and validated on cloud-hosted devices with minimal code.

For example, in research fields focused on developing compounds or drugs, a specialized model trained on specific scientific data may be necessary. Developers can upload such models to Qualcomm’s AI Hub and deploy them on AI PCs within their organizations, enabling local access instead of relying on cloud solutions.

This approach applies across various industries. Having models optimized for PCs reduces latency and facilitates faster iterations, enhancing overall efficiency and responsiveness.