DeepSeek OCR, MiniMax M2.1, and Qwen3-VL-8B-Instruct models are now available on SageMaker JumpStart

AWS SageMaker JumpStart Model Updates

AWS has introduced three new models in Amazon SageMaker JumpStart: DeepSeek OCR, MiniMax M2.1, and Qwen3-VL-8B-Instruct. These models offer specialized capabilities in document intelligence, multilingual coding, and advanced multimodal reasoning, enhancing the ability to build sophisticated AI applications.

New Models Overview

• DeepSeek OCR: Specializes in visual-text compression for document processing, capable of extracting structured information from various document types.
• MiniMax M2.1: Optimized for coding, tool use, and long-horizon planning, supporting multilingual software development and complex workflows.
• Qwen3-VL-8B-Instruct: Offers superior text understanding, visual perception, and reasoning capabilities, along with enhanced interaction features.

What to do

• Deploy these models via the SageMaker JumpStart model catalog in the SageMaker console or using the SageMaker Python SDK.
• Refer to the Amazon SageMaker JumpStart documentation for deployment and usage instructions.

Source: AWS release notes

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.