Gemma 4 models are now available on Amazon Bedrock in AWS GovCloud (US-West)

Gemma 4 Models on Amazon Bedrock in AWS GovCloud (US-West)

Google DeepMind's Gemma 4 family of open-weight models is now available on Amazon Bedrock in AWS GovCloud (US-West). These models enable the creation of generative AI applications across various workflows including reasoning, multimodal understanding, agentic, and software engineering.

Model Variants

• Gemma 4 31B: Ideal for reasoning and coding-heavy workloads with a 256K-token context window.
• Gemma 4 26B-A4B: Optimized for cost and latency-sensitive workloads.
• Gemma 4 E2B: The smallest variant, designed for low-latency interactive use cases.

Features

• Dense and mixture-of-experts (MoE) architectures
• Built-in reasoning and native function calling
• Support for 35+ languages
• Multimodal input (text, image, video, audio)
• Improved support for tool calling, structured output, reasoning, and response streaming

What to do

• Visit the Gemma 4 model detail pages in the AWS documentation to get started.

Source: AWS release notes

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.