OpenFold3 on SageMaker lets you predict protein structures in the cloud
What is OpenFold3 on Amazon SageMaker JumpStart: Predict biomolecular structures?
OpenFold3-preview is now available as a SageMaker JumpStart model, enabling you to run asynchronous inference on proteins, DNA, RNA and ligand complexes directly in your AWS account. It supports multi-GPU parallelism, custom multiple sequence alignments for higher accuracy, and keeps your data private.
Who it is for
Researchers and drug developers who need fast, on-demand 3-D biomolecular models can spin up an endpoint without managing any infrastructure.
How to try it
Open the SageMaker console, choose JumpStart, and deploy the OpenFold3 model.
The story so far
Early Signal first spotted OpenFold3 on Amazon SageMaker JumpStart: Predict biomolecular structures on November 13, 2026. Early Signal files it under Inference.
Questions about OpenFold3 on Amazon SageMaker JumpStart: Predict biomolecular structures
- How do I try OpenFold3 on Amazon SageMaker JumpStart: Predict biomolecular structures?
- Open the SageMaker console, choose JumpStart, and deploy the OpenFold3 model.
- What do I need to run OpenFold3 on Amazon SageMaker JumpStart: Predict biomolecular structures?
- AWS account with SageMaker permissions and a GPU-enabled instance (e.g., ml.p4d.24xlarge).