---
格式版本: 2
标题: "NVIDIA Nemotron 3.5 Lightning model is now available on Amazon SageMaker JumpStart"
原文链接: "https://aws.amazon.com/cn/about-aws/whats-new/2026/01/nvidia-nemotron-3.5-lightning-on-sagemaker-jumpstart/"
发布日期: "2026-08-11"
发布时间校准状态: "found"
发布时间需复核: "否"
发布时间来源: "llm:local:original_script_field"
发布时间证据: "postDateTime: 2026-08-11T15:21:00Z"
发布时间校准原因: "该日期来自脚本字段中的postDateTime，明确标注为文章发布时间，且无其他候选冲突。"
发布时间校准置信度: "1"
发布时间候选数量: 1
发布时间严格候选数量: 0
发布时间原页读取状态: "source template page reused from URL open"
发布时间未找到原因: ""
发布时间校准时间: "2026-08-12T21:22:57+08:00"
发布时间仲裁状态: "confirmed"
发布时间仲裁尝试次数: 1
发布时间仲裁耗时毫秒: 6678
发现时间: "2026-08-12T21:17:42+08:00"
入库时间: "2026-08-12T13:23:06.336Z"
来源平台: "固定入口"
搜索渠道: "fixed_url"
搜索词: "https://aws.amazon.com/new"
匹配关键词:
  - "throughput"
  - "AI"
相关厂家:
  - "AWS"
  - "NVIDIA"
相关专家:
  []
内容类型: "网页"
抓取工具: "Free Fetch + Defuddle"
清洗工具: "Defuddle Markdown + Defuddle/Readability 正文提取"
原始附件:
  []
AI优质: "否"
AI打分: 33
AI分档: "非优质"
AI质检状态: "不通过"
AI打分理由: "正文仅介绍NVIDIA AI模型在SageMaker上的可用性，未涉及超节点/AI Rack/机柜级系统、供电、散热、互连等硬件架构或量产落地，与项目主题无关。"
AI质检模型: "ali-deepseek-v4-flash"
AI质检时间: "2026-08-12T21:27:59+08:00"
AI主题相关性: 1
AI来源权威性: 12
AI新颖性: 10
AI技术细节: 2
AI商业部署信号: 3
AI完整性: 5
采集批次: "2026年8月12日20点58分23秒"
采集批次ID: "20260812-205823-234"
去重键: "https://aws.amazon.com/cn/about-aws/whats-new/2026/01/nvidia-nemotron-3.5-lightning-on-sagemaker-jumpstart"
---

NVIDIA's Nemotron 3.5 Lightning is now available on Amazon SageMaker JumpStart, giving AWS customers access to the fastest open model in its class for persistent agent workloads and rapid task execution.

Nemotron 3.5 Lightning is engineered for persistent agents and high-throughput enterprise automation across domains including personal assistants, financial document processing, cybersecurity triage, and telecom operations. Built on a hybrid Mixture-of-Experts (MoE) architecture with 30B total parameters and just 3B active per forward pass, it achieves up to 4x the throughput (~410 tokens/sec) and 30% faster task completion over comparable models. Distilled from Nemotron 3 Ultra, it handles up to 1M tokens of context via DFlash speculative decoding and integrates directly with popular agent harnesses. The model is fully open-trained on open datasets thereby allowing enterprises to post-train for their own tools, workflows, and policies, and deploy with complete ownership across edge, on-premises, or cloud infrastructure.

With SageMaker JumpStart, customers can deploy this model in a few clicks to power their specific AI workloads.

To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the [Amazon SageMaker JumpStart documentation](https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html).