Amazon SageMaker AI serverless model customization now supports full fine-tuning
News
This article announces that Amazon SageMaker AI serverless model customization now supports full fine-tuning for over 25 open-source models.
- Supports popular models from gpt-oss, Gemma, Llama, Nemotron, and Qwen families
- Full fine-tuning updates all model parameters for deeper domain-specific adaptation
- Complements parameter-efficient methods like LoRA for specialized use cases
- SageMaker manages infrastructure provisioning and training orchestration
- Available in US East (N. Virginia), US West (Oregon), Asia Pacific (Tokyo), and Europe (Ireland)
- Access via JumpStart and Models page in SageMaker Studio or Python SDK
Serverless full fine-tuning enables organizations to customize models for complex reasoning patterns and domain knowledge without managing infrastructure.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Dec 3
2025
2025
New serverless customization in Amazon SageMaker AI accelerates model fine-tuning
Dec 3
2025
2025
New serverless model customization capability in Amazon SageMaker AI
Jun 30
2026
2026
Amazon SageMaker AI now supports serverless model customization for Gemma 4 models
Apr 22
2026
2026
Amazon SageMaker AI now supports serverless model customization for Qwen3.5 models
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.