---
格式版本: 2
标题: "Import NVIDIA Nemotron 3.5 Lightning Models into OCI Generative AI"
原文链接: "https://docs.oracle.com/en-us/iaas/releasenotes/generative-ai/nvidia-nemotron-3-5-lightning.htm"
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:scrape:strict_html_body"
发布时间证据: "span class=vl-relnotedate: August 11, 2026"
发布时间校准原因: "正文中明确标注的发布说明日期（vl-relnotedate），且位于标题附近，符合最高优先级。"
发布时间校准置信度: "1"
发布时间候选数量: 16
发布时间严格候选数量: 5
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: "2026-08-12T21:46:54+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: 6533
发现时间: "2026-08-12T21:42:48+08:00"
入库时间: "2026-08-12T13:47:01.008Z"
来源平台: "固定入口"
搜索渠道: "fixed_url"
搜索词: "https://docs.oracle.com/en-us/iaas/releasenotes"
匹配关键词:
  - "AI"
  - "deployment"
相关厂家:
  - "Oracle"
  - "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: 25
AI分档: "非优质"
AI质检状态: "不通过"
AI打分理由: "内容仅为Oracle OCI导入NVIDIA Nemotron 3.5 Lightning模型的说明，未涉及超节点/AI Rack/机柜级系统架构、互连、供电、散热或量产落地等核心主题，与项目关注范围无关。"
AI质检模型: "ali-deepseek-v4-flash"
AI质检时间: "2026-08-12T21:48:03+08:00"
AI主题相关性: 0
AI来源权威性: 15
AI新颖性: 5
AI技术细节: 0
AI商业部署信号: 5
AI完整性: 0
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://docs.oracle.com/en-us/iaas/releasenotes/generative-ai/nvidia-nemotron-3-5-lightning.htm"
---

You can now import the following NVIDIA Nemotron 3.5 Lightning models into OCI Generative AI, create endpoints for them, and use them in the Generative AI service:

- [`nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16`](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16)
	**Model capability:** `TEXT_TO_TEXT`
	**Minimum dedicated AI cluster unit shapes:** `A100_40G_X2`, `A100_80G_X1`, `H100_X1`, `H200_X1`, and `B200_X1`
- [`nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4`](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4)
	**Model capability:** `TEXT_TO_TEXT`
	**Minimum dedicated AI cluster unit shapes:** `H100_X1`, `H200_X1`, and `B200_X1`

For the complete list of models that you can import, see [Models for Import](https://docs.oracle.com/iaas/Content/generative-ai/imported-models.htm). For available hardware and deployment steps, see [Managing Imported Models](https://docs.oracle.com/iaas/Content/generative-ai/manage-imported-models.htm#imported-models).