Amazon SageMaker AI now supports serverless model customization for Gemma 4 models

Amazon SageMaker AI now supports serverless model customization for Gemma 4 models using multiple fine-tuning techniques.

• Customize Gemma 4 E4B and 31B models with supervised fine-tuning, direct preference optimization, and reinforcement fine-tuning
• Extend customization to Nova, Nemotron 3, Qwen, Llama, gpt-oss, and DeepSeek model families
• Tailor foundation models with proprietary data for domain-specific tasks and organizational alignment
• Serverless infrastructure handles provisioning and orchestration; pay only for usage
• Available in US East (N. Virginia), US West (Oregon), Asia Pacific (Tokyo), and EU (Ireland)

Serverless customization simplifies model adaptation by eliminating infrastructure management overhead.