NewRun Gen AI models with GenieX
On‑Device AI Starts Here
Optimize, validate, and deploy any model in a few lines of code.
Latest Models
Your AI Development Stack
Qualcomm® AI HubAI Hub
GenieX
NewShip the latest Gen AI models in a few lines of code with GenieX—an open‑source toolkit with a unified runtime for NPU, GPU, and CPU.
Qualcomm® AI HubAI Hub
Models
Access 300+ ML and Gen AI models optimized for your device. Compare performance metrics, grab the exact model you need, and ship your next on‑device experience today.
Qualcomm® AI HubAI Hub
Apps
Turn optimized models into native applications. Our sample app repositories give you the code templates and step‑by‑step guides to ship your on‑device AI faster.
Qualcomm® AI HubAI Hub
Workbench
Optimize your custom trained model for Qualcomm devices with Workbench:
- Convert your trained PyTorch or ONNX models to any on‑device runtime: LiteRT, ONNX Runtime, or Qualcomm AI Runtime
- Quantize and fine‑tune for accuracy
- Profile and run inference on 50+ types of Qualcomm devices hosted in our cloud
An End‑to‑End Workflow for Optimized On‑Device AI
- Start
AI HubModels
Your own modelChoose your starting point — a custom trained model or one from our collection and kick off your workflow.
- AI Hub
Workbench
compilerun inferencequantizeAI HubGenieX
NewEasily compile, run inference and quantize your model to optimize for edge devices.
- AI Hub
Apps
Your own appDeploy
on deviceCustomize sample application code to easily deploy your optimized model on device.
AI Hub Ecosystem
Collaborations designed to accelerate your AI journey
Models for All Solutions
Mobile
Enabling Intelligent Connections and Personalized Applications Across Devices
Compute
Endless Possibilities on a Powerful Device, Built for AI
Automotive
Unlocking a New Era of Mobility
IoT
Deploy Real‑Time AI to Various Devices Providing Next‑Generation User Experiences
