---
格式版本: 2
标题: "Compatible Mistral Models"
原文链接: "https://docs.oracle.com/en-us/iaas/Content/generative-ai/imported-mistral-models.htm"
发布日期: "2026-08-12"
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: 2026-08-12 02:33:32Z"
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: "2026-08-12T21:48:07+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: "2026-08-12T21:42:48+08:00"
入库时间: "2026-08-12T13:48:07.080Z"
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"
  - "performance"
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: 20
AI分档: "非优质"
AI质检状态: "不通过"
AI打分理由: "页面为Oracle文档，聚焦Mistral模型导入与配置，仅列出GPU型号作为最低资源，无超节点/AI Rack/机柜级系统、供电、散热、互连等硬件架构细节，与项目主题无关。"
AI质检模型: "ali-deepseek-v4-flash"
AI质检时间: "2026-08-12T21:48:33+08:00"
AI主题相关性: 2
AI来源权威性: 10
AI新颖性: 2
AI技术细节: 2
AI商业部署信号: 0
AI完整性: 4
AI摘要: "Oracle OCI Generative AI 支持从 Hugging Face 和 OCI Object Storage 导入 Mistral 系列大模型并创建端点，可用作文本生成或嵌入，涵盖 Magistral-Small-2509。"
AI摘要模型: "ali-deepseek-v4-flash"
AI摘要时间: "2026-09-07T03:39:37.901Z"
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/Content/generative-ai/imported-mistral-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.

These models have a high-performance, decoder-only Transformer architecture featuring Sliding Window Attention (SWA) for efficient long-context handling and optional Grouped Query Attention (GQA) for improved scalability. For more details, see [Mistral](https://huggingface.co/docs/transformers/model_doc/mistral) in the Hugging Face documentation.

## Mistral

| Hugging Face Model ID | Model Capability | Minimum Dedicated AI Cluster Unit Shape |
| --- | --- | --- |
| [mistralai/Magistral-Small-2509](https://huggingface.co/mistralai/Magistral-Small-2509) | TEXT\_TO\_TEXT | - A100\_40G\_X4 - A100\_80G\_X2 - H100\_X2 - H200\_X2 |
| [mistralai/Mistral-Medium-3.5-128B](https://huggingface.co/mistralai/Mistral-Medium-3.5-128B) | TEXT\_TO\_TEXT |  |
| [mistralai/Devstral-2-123B-Instruct-2512](https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512) | TEXT\_TO\_TEXT |  |
| [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) | TEXT\_TO\_TEXT | A100\_80G\_X2 |
| [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | TEXT\_TO\_TEXT | A100\_80G\_X1 |
| [intfloat/e5-mistral-7b-instruct](https://huggingface.co/intfloat/e5-mistral-7b-instruct) | EMBEDDING | A10\_X1 |