Amazon SageMaker AI now supports serverless model customization for Muse Glimmer, Qwen 3.8 and Ministral 3 models

This article announces serverless model customization support for Muse Glimmer, Qwen 3.8, and Ministral 3 models on Amazon SageMaker AI.

• Customize models using supervised fine-tuning (SFT), direct preference optimization (DPO), and reinforcement fine-tuning (RFT)
• Choose between low-rank adaptation (LoRA) or full fine-tuning techniques
• Tailor foundation models with proprietary data to reduce cost and latency
• SageMaker AI handles infrastructure provisioning and training orchestration automatically
• Available in US East (N. Virginia), US West (Oregon), Asia Pacific (Tokyo), and Europe (Ireland)
• Access via SageMaker Studio, Python SDK, or Agent skills with coding assistants

Serverless customization enables organizations to adapt models to specific domains and workflows without managing infrastructure.