TabPFN-2.5 Now Available on AWS SageMaker: One-Click Deployment in Your AWS Environment
TL;DR:
- TabPFN-2.5 is now available on AWS SageMaker Marketplace
- Deploy with a single click, no manual infrastructure setup required
- All data and inference stay within your AWS account - complete data privacy
We're excited to announce that TabPFN-2.5 is now available on AWS SageMaker Marketplace. You can now run TabPFN on your own without ever leaving your network. Deploy it in your AWS account with a single click. AWS handles infrastructure setup, GPU configuration and inference framework.
How It Works
Subscribe to TabPFN in the AWS SageMaker Marketplace, and AWS automatically provisions and configures everything within your account. Your data and all inference requests stay in your private AWS networks. Once deployed, you can run classification and regression tasks that return predictions instantly.
Deployment
Getting started:
- Navigate to AWS SageMaker Marketplace and search for "TabPFN-2.5" in model packages
- Click "View Purchase Options" and then "Subscribe" at the bottom right
- AWS automatically handles GPU provisioning and setup
What gets deployed:
- TabPFN running on your specified GPU resources
- Inference endpoints ready to use immediately
- Everything contained within your AWS account
Key Benefits
- Complete data privacy: Everything runs in your AWS account, your data never leaves your infrastructure
- Minimal infrastructure work: AWS handles GPU provisioning, driver configuration, and deployment
- Fast predictions for classification and regression at scale
- AWS native: Seamless integration with your existing environment and security policies
This is ideal for teams that need to keep data within AWS, or want to use TabPFN without managing infrastructure.
Resources
Find TabPFN in AWS SageMaker Marketplace →
- Full Documentation → Complete setup guides, API reference, and configuration options
- Example Scripts → Working examples for classification and regression tasks
- Get Support → Any issue along the way? Our team is here to help at support@priorlabs.ai
