---
格式版本: 2
标题: "Compatible Alibaba Models"
原文链接: "https://docs.oracle.com/en-us/iaas/Content/generative-ai/imported-alibaba-models.htm"
发布日期: "2026-09-04"
发布时间校准状态: "found"
发布时间需复核: "否"
发布时间来源: "rule:scrape:strict_html_body"
发布时间证据: "cpp-last-modified-time: 2026-09-04 19:45:20Z"
发布时间校准原因: "规则确认唯一严格发布时间，来源 scrape:strict_html_body"
发布时间校准置信度: "high"
发布时间候选数量: 6
发布时间严格候选数量: 2
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: "2026-09-07T23:18:15+08:00"
发布时间仲裁状态: "skipped"
发布时间仲裁尝试次数: 0
发布时间仲裁耗时毫秒: 0
发现时间: "2026-09-07T23:16:23+08:00"
入库时间: "2026-09-07T15:20:26.174Z"
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"
相关厂家:
  - "Oracle"
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: 32
AI分档: "非优质"
AI质检状态: "不通过"
AI打分理由: "正文主线为Oracle云服务可导入的Qwen模型清单及最低专用AI集群单元规格，属于模型接入说明，并非讨论超节点/AI Rack/机架级基础设施。来源为Oracle官方文档，权威性尚可，但非针对本库主题。内容仅为Hugging Face模型ID与最低GPU规格映射表，无rack-scale架构、互连、供电、液冷、量产或部署细节；历史对照亦无新增机架级事实。未命中任何高价值准入通道，命中正文不可用/主题错配边界，故判非优质。"
AI质检模型: "zj-deepseek-v4-flash"
AI质检时间: "2026-09-07T23:20:40+08:00"
AI主题相关性: 4
AI来源权威性: 12
AI新颖性: 6
AI技术细节: 3
AI商业部署信号: 2
AI完整性: 5
AI评分提示词版本: "v17-精简生产版"
AI评分提示词SHA256: "48fb9777f386026761b4873eaff30807694fb11e9b352d7c69bf2dfde750cc7d"
AI评分知识库版本: "knowledge_base_v1-20260819+runtime.100"
AI评分知识库SHA256: "7fe4568b9de9fc322c105ece08d18efab5b9b86f27dea6eb043b9a4d273bde60"
AI评分知识库检索词: "[\"Oracle\",\"https://docs.oracle.com/en-us/iaas/releasenotes\",\"Qwen/Qwen3.8-2.4T-A95B-FP8\",\"OCI\",\"ID\",\"Qwen/Qwen3-Next-80B-A3B-Instruct\",\"huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct\",\"TEXT\",\"A100\",\"H100\",\"H200\",\"huggingface.co/Qwen/Qwen3.8-2.4T-A95B-FP8\"]"
AI评分知识库命中: "[{\"id\":\"runtime-dccd09f98e2ca028070793f0\",\"title\":\"https://blogs.oracle.com/cloud-infrastructure/oci-achieves-nvidia-exemplar-cloud\",\"sourceType\":\"ai_excellent_article\",\"time\":\"\",\"matchedTerms\":[\"Oracle\",\"OCI\",\"ID\"],\"rank\":-12.903119428255316},{\"id\":\"runtime-f42510f490b4e8271c10e963\",\"title\":\"NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Watt\",\"sourceType\":\"ai_excellent_article\",\"time\":\"\",\"matchedTerms\":[\"OCI\",\"ID\",\"TEXT\",\"H200\"],\"rank\":-11.396207907512444},{\"id\":\"runtime-66d1ddc58948150bffee973a\",\"title\":\"Delivering Vera: NVIDIA’s First CPU Built for Agents Is Shipping Now\",\"sourceType\":\"ai_excellent_article\",\"time\":\"\",\"matchedTerms\":[\"Oracle\",\"OCI\",\"ID\",\"TEXT\"],\"rank\":-11.365000564701992},{\"id\":\"runtime-0210d17c29c694da454d0e78\",\"title\":\"HPE caps stellar Q3 with Oracle ‘gigawatt scale’ networking deal\",\"sourceType\":\"ai_excellent_article\",\"time\":\"\",\"matchedTerms\":[\"Oracle\",\"OCI\",\"ID\"],\"rank\":-10.088191569119248},{\"id\":\"july-correct-0093\",\"title\":\"NVIDIA Exemplar Cloud: Lessons for Unlocking Full Performance on AI Infrastructure\",\"sourceType\":\"labeled_article\",\"time\":\"2026-07\",\"matchedTerms\":[\"ID\",\"H100\",\"H200\"],\"rank\":-9.04034311198595}]"
采集批次: "2026年9月7日23点15分57秒"
采集批次ID: "20260907-231557-722"
去重键: "https://docs.oracle.com/en-us/iaas/Content/generative-ai/imported-alibaba-models.htm"
---

You can import large language models from Hugging Face and OCI Object Storage buckets into OCI Generative AI, create endpoints for those models, and use them in the Generative AI service.

Alibaba Qwen model family, feature advanced multilingual and multimodal capabilities. For model cards on Hugging Face, see the links in the following tables.

## Qwen 3 Next

| Hugging Face Model ID | Model Capability | Minimum Dedicated AI Cluster Unit Shape |
| --- | --- | --- |
| [Qwen/Qwen3-Next-80B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct) | TEXT\_TO\_TEXT | - A100\_80G\_X4 - H100\_X4 - H200\_X4 |

## Qwen 3.8

| Hugging Face Model ID | Model Capability | Minimum Dedicated AI Cluster Unit Shape |
| --- | --- | --- |
| [Qwen/Qwen3.8-2.4T-A95B-FP8](https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B-FP8) | TEXT\_TO\_TEXT | - B200\_X16 |

## Qwen 3.6

| Hugging Face Model ID | Model Capability | Minimum Dedicated AI Cluster Unit Shape |
| --- | --- | --- |
| [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) | IMAGE\_TEXT\_TO\_TEXT | - A100\_80GB\_X2 - H100\_X2 - H200\_X1 - B200\_X1 |

## Qwen 3.5

| Hugging Face Model ID | Model Capability | Minimum Dedicated AI Cluster Unit Shape |
| --- | --- | --- |
| [Qwen/Qwen3.5-397B-A17B](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) | IMAGE\_TEXT\_TO\_TEXT | - H200\_X8 - B300\_X4 |
| [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) | IMAGE\_TEXT\_TO\_TEXT | - A100\_80GB\_X1 - H100\_X1 - H200\_X1 - B200\_X1 |

## Qwen Image

| Hugging Face Model ID | Model Capability | Minimum Dedicated AI Cluster Unit Shape |
| --- | --- | --- |
| [Qwen/Qwen-Image](https://huggingface.co/Qwen/Qwen-Image) | TEXT\_TO\_IMAGE | A100\_80G\_X1 |
| [Qwen/Qwen-Image-Edit](https://huggingface.co/Qwen/Qwen-Image-Edit) | IMAGE\_TEXT\_TO\_IMAGE | A100\_80G\_X1 |
| [Qwen/Qwen-Image-2512](https://huggingface.co/Qwen/Qwen-Image-2512) | TEXT\_TO\_IMAGE | A100\_80G\_X1 |
| [Qwen/Qwen-Image-Edit-2511](https://huggingface.co/Qwen/Qwen-Image-Edit-2511) | IMAGE\_TEXT\_TO\_IMAGE | A100\_80G\_X1 |
| [Qwen/Qwen-Image-Edit-2509](https://huggingface.co/Qwen/Qwen-Image-Edit-2509) | IMAGE\_TEXT\_TO\_IMAGE | A100\_80G\_X1 |

## Qwen Q (Reasoning)

| Hugging Face Model ID | Model Capability | Minimum Dedicated AI Cluster Unit Shape |
| --- | --- | --- |
| [Qwen/QwQ-32B](https://huggingface.co/Qwen/QwQ-32B) | TEXT\_TO\_TEXT | A100\_80G\_X2 |

## Qwen 3

| Hugging Face Model ID | Model Capability | Minimum Dedicated AI Cluster Unit Shape |
| --- | --- | --- |
| [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) | EMBEDDING | A10\_X1 |
| [Qwen/Qwen3-Embedding-4B](https://huggingface.co/Qwen/Qwen3-Embedding-4B) | EMBEDDING | A10\_X2 |
| [Qwen/Qwen3-Embedding-8B](https://huggingface.co/Qwen/Qwen3-Embedding-8B) | EMBEDDING | A100\_80G\_X1 |
| [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen3-14B](https://huggingface.co/Qwen/Qwen3-14B) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) | TEXT\_TO\_TEXT | A100\_80G\_X2 |
| [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen3-30B-A3B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507) | TEXT\_TO\_TEXT | A100\_80G\_X2 |
| [Qwen/Qwen3-235B-A22B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507) | TEXT\_TO\_TEXT | H100\_X8 |
| [Qwen/Qwen3-VL-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct) | IMAGE\_TEXT\_TO\_TEXT | H100\_X2 |
| [Qwen/Qwen3-VL-30B-A3B-Instruct-FP8](https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct-FP8) | IMAGE\_TEXT\_TO\_TEXT | - H100\_X2 - H200\_X2 |
| [Qwen/Qwen3-VL-235B-A22B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct) | IMAGE\_TEXT\_TO\_TEXT | H100\_X8 |

## Qwen 2.5

| Hugging Face Model ID | Model Capability | Minimum Dedicated AI Cluster Unit Shape |
| --- | --- | --- |
| [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) | TEXT\_TO\_TEXT | A100\_80G\_X2 |
| [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) | TEXT\_TO\_TEXT | A100\_80G\_X2 |
| [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct) | TEXT\_TO\_TEXT | A100\_80G\_X4 |
| [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) | IMAGE\_TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) | IMAGE\_TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen2.5-VL-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct) | IMAGE\_TEXT\_TO\_TEXT | A100\_80G\_X2 |
| [Qwen/Qwen2.5-VL-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct) | IMAGE\_TEXT\_TO\_TEXT | A100\_80G\_X4 |

## Qwen 2

| Hugging Face Model ID | Model Capability | Minimum Dedicated AI Cluster Unit Shape |
| --- | --- | --- |
| [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct) | TEXT\_TO\_TEXT | A100\_80G\_X4 |
| [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) | IMAGE\_TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct) | IMAGE\_TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [Qwen/Qwen2-VL-72B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct) | IMAGE\_TEXT\_TO\_TEXT | A100\_80G\_X4 |