Amazon SageMaker AI now supports serverless model customization for Gemma 4 models
Amazon SageMaker ยท 2026-06-30
Actions
Technical Details
| Regions | us-east-1, us-west-2, ap-northeast-1, eu-west-1 |
|---|---|
| Cost Impact | Decrease |
What This Means
For DevOps Teams
Update your AI workflows to leverage serverless model customization for Gemma 4 models, utilizing supervised fine-tuning, direct preference optimization, and reinforcement fine-tuning to adapt models without managing infrastructure, resulting in reduced operational toil and focused resource allocation.
For Platform Teams
Adopt serverless model customization for Gemma 4 models to integrate advanced AI capabilities into your platform, reducing the need for manual infrastructure management and enabling faster deployment of tailored AI models.
For Executives
Evaluate the new serverless model customization for Gemma 4 models to enhance AI capabilities, reduce infrastructure management overhead, and align model outputs with organizational standards, leading to improved accuracy and performance on domain-specific tasks.
Source
Related Amazon SageMaker Updates
- Amazon SageMaker AI cuts generative AI inference scale-out time by up to half with automatic container image caching (2026-06-30)
- Amazon SageMaker AI Announces New observability capability For Inference Endpoints (2026-06-18)
- Ministral-3-14B-Instruct for multimodal reasoning and agentic AI is now available in Amazon SageMaker JumpStart (2026-06-18)
- all-MiniLM-L12-v2 for semantic search and sentence similarity is now available in Amazon SageMaker JumpStart (2026-06-18)
- AWS Glue Interactive Sessions now support Spark Connect for interactive workloads (2026-06-17)