Qwen3.6-35B-A3B-NVFP4 and Wan2.1-T2V-1.3B-Diffusers models now available on Amazon SageMaker JumpStart

This article announces the availability of two new foundation models on Amazon SageMaker JumpStart: NVIDIA's Qwen3.6-35B-A3B-NVFP4 and Alibaba's Wan2.1-T2V-1.3B-Diffusers.

• Qwen3.6-35B-A3B-NVFP4 optimized for agentic coding, multimodal reasoning, and long-context understanding with 262K-token context window
• Supports multi-token prediction and tool calling for multi-step agent pipelines with reduced memory footprint via NVFP4 quantization
• Wan2.1-T2V-1.3B-Diffusers generates high-quality text-to-video on consumer-grade hardware requiring only 8.19 GB VRAM
• Produces 5-second 480p videos in ~4 minutes on RTX 4090, making it highly accessible for video generation tasks
• Deploy models with few clicks via SageMaker JumpStart console or Python SDK

These models expand SageMaker JumpStart's foundation model portfolio, enabling customers to deploy specialized AI solutions for coding and video generation on AWS infrastructure.