SageMaker AI began supporting supervised and reinforcement fine-tuning (SFT and RFT) of Qwen3.5 4B, 9B, and 27B parameter models serverlessly. This allows users to adapt the base open-weight Qwen3.5 models to specific domains and workflows without managing compute infrastructure.
Serverless customization handles provisioning and orchestration automatically, focusing user effort on data and evaluation. This capability is available in multiple AWS regions, enabling more precise and efficient tailoring of foundational AI models to organizational needs and terminology.
Source & further reading
Amazon SageMaker AI now supports serverless model customization for Qwen3.5 models ↗Source published 2026-04-22. This report was prepared with AI assistance from the linked primary-source material. Claims and limitations should be checked against the original announcement or research.