JA EN
shiichan

The multimodal Gemma-4-E2B-it model lands in SageMaker JumpStart!

AWS What's New ★★★★ View Markdown
#aws#ai

Hi everyone, it's Shii-chan! Today's news is about a new Google DeepMind model joining SageMaker JumpStart, and I can't stop being excited about it.

AWS What's New aws.amazon.com

What was announced?

According to AWS What's New, Google DeepMind's multimodal, instruction-tuned model called Gemma-4-E2B-it is now available in Amazon SageMaker JumpStart. That means the lineup of foundation models you can pick from in SageMaker JumpStart has grown by one more.

This model is optimized for efficient local execution, and its whole point is letting you build AI applications easily on AWS infrastructure.

Why it matters

Many existing foundation models handle text only, or at best text and images. Gemma-4-E2B-it goes further and accepts text, image, and audio input all at once. It also has a built-in reasoning mode that lets it think step-by-step before answering, so it's not just for quick replies — it can also handle situations where you want it to reason things through.

What changes

Gemma-4-E2B-it takes text, image, and audio as input and generates text output. Here's what it supports.

  • Image understanding: object detection, document parsing, screen/UI understanding, chart comprehension, and OCR
  • Video understanding
  • Native function calling for agentic workflows
  • Code generation, completion, and correction
  • Multilingual support across dozens of languages

Beyond simple chatbot-style responses, this means a single model can cover a lot of ground, from reading documents and screenshots to running agentic workflows that call tools on their own.

Dive Deep

There are two ways to deploy it.

  • From the Models section of SageMaker Studio, with just a few clicks
  • Programmatically, using the SageMaker Python SDK to deploy it to your own AWS account

For the full deployment steps and parameters, check out the Amazon SageMaker JumpStart documentation.

Wrap-up

  • Google DeepMind's multimodal model Gemma-4-E2B-it is now available in SageMaker JumpStart
  • It accepts text, image, and audio input, with a built-in reasoning mode
  • It covers image/video understanding, agentic function calling, code generation/completion/correction, and multilingual support
  • You can deploy it in a few clicks from SageMaker Studio or via the Python SDK

If you want to build a multimodal, agentic app on AWS that can read images and documents, this is a great option to try!

Related posts