Yes, you can deploy a SageMaker trained model outside of SageMaker. How to do that exactly and the documentation depends on the framework and framework version.
For example lets say you want to deploy a TensorFlow 2.X model outside of SageMaker, you would use something https://www.tensorflow.org/tfx/tutorials/serving/rest_simple.
How to get logs or print statements from SageMaker PyTorch deployed endpoint?asked 3 months ago
Can Sagemaker-trained models be deployed to non-Sagemaker endpoints?asked 2 years ago
How to register a multi container model to a model registry?
How to search for Amazon SageMaker Models using Tags?
Host multiple TensorFlow computer vision models using Amazon SageMaker multi-model endpointsasked 10 months ago
Can GraphQL be deployed to Elastic Beanstalk?Accepted Answerasked 2 years ago
Can't deployed vm that I downloadasked 5 months ago
Can a SG be deployed using SSM/PS to all Ec2 instances?Accepted Answerasked 9 months ago
Is any component of Sagemaker still involved in production inferencingasked 14 days ago
Can I use Amazon Rekognition to find cropped versions of an image?asked 4 months ago