Gemma-4-31B-it-assistant and Gemma-4-31B-IT-NVFP4 models now available on Amazon SageMaker JumpStart

New Models Available on Amazon SageMaker JumpStart

Google DeepMind's Gemma-4-31B-it-assistant and NVIDIA's Gemma-4-31B-IT-NVFP4 models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers.

Gemma-4-31B-it-assistant

Built for multimodal reasoning, coding, and agentic workflows, this model handles text and image inputs, generating text output with a 256K-token context window and support for over 140 languages. It features a hybrid attention mechanism and native function calling for building autonomous agents.

Gemma-4-31B-IT-NVFP4

This model delivers the same capabilities at a fraction of the memory footprint, quantized to 4-bit FP4 precision, reducing memory usage to ~18.5 GB and achieving approximately 2.5x faster inference while retaining 97–99% of the original model's quality. Ideal for cost-efficient, high-throughput production deployments.

What to do

• Navigate to the SageMaker JumpStart model catalog in the SageMaker console.
• Use the SageMaker Python SDK to deploy the models to your AWS account.

For more information, see the Amazon SageMaker JumpStart documentation.

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.