NVIDIA Nemotron 3.5 Lightning AI Model Now Available on Amazon SageMaker JumpStart
NVIDIA's Nemotron 3.5 Lightning model is now available on Amazon SageMaker JumpStart, providing AWS customers with access to a fast, open model for persistent agent workloads. Engineered for high-throughput enterprise automation, this 30B-parameter hybrid Mixture-of-Experts (MoE) model offers up to 4x higher throughput and 30% faster task completion than comparable models. It supports up to 1M tokens of context and is open-trained, allowing enterprises to post-train and deploy with full ownership across various infrastructures. Customers can deploy the model via the SageMaker console or Python SDK to power their specific AI applications.
Features (1) ›
- NVIDIA Nemotron 3.5 Lightning model added to SageMaker JumpStart
The NVIDIA Nemotron 3.5 Lightning model, designed for persistent agent workloads and high-throughput enterprise automation, is now accessible on Amazon SageMaker JumpStart. This 30B-parameter hybrid MoE model offers significantly higher throughput and faster task completion, supporting up to 1M tokens of context and allowing for enterprise post-training and deployment.
https://aws.amazon.com/about-aws/whats-new/2026/01/nvidia-nemotron-3.5-lightning-on-sagemaker-jumpstart/
Related releases
- AWS Blog: Unified Access Control for Enterprise Lakehouses AWS Big Data Blog ·
- AWS Glue integrates with SageMaker Unified Studio for one-click data access AWS What's New ·
- NVIDIA and Qwen AI Models Now on Amazon SageMaker JumpStart AWS What's New ·
- New GLM-5.2 FP8, Nemotron-Nano-12B-v2, and GLM-OCR models on SageMaker JumpStart AWS What's New ·
- New AI Models from Redis, JetBrains, and LightOn Now on SageMaker JumpStart AWS What's New ·
- FLUX.2-small-decoder and gemma-4-12B-it Models Now on Amazon SageMaker JumpStart AWS What's New ·