---
格式版本: 2
标题: "Compatible MiniMax Models"
原文链接: "https://docs.oracle.com/en-us/iaas/Content/generative-ai/imported-minimax-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: "2026-08-12T21:55:03+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: "2026-08-12T13:55:03.827Z"
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: 30
AI分档: "非优质"
AI质检状态: "不通过"
AI打分理由: "内容为Oracle文档中关于导入MiniMax模型的服务说明，仅提及H200/B200作为最小单元形状，未涉及超节点、AI Rack、机柜级系统架构、供电散热互连等核心主题，技术细节和商业信号均不足。"
AI质检模型: "ali-deepseek-v4-flash"
AI质检时间: "2026-08-12T21:55:11+08:00"
AI主题相关性: 5
AI来源权威性: 12
AI新颖性: 5
AI技术细节: 5
AI商业部署信号: 2
AI完整性: 1
AI摘要: "Oracle OCI Generative AI 现已支持从 Hugging Face 或对象存储导入 MiniMax 系列大语言模型并创建端点使用。"
AI摘要模型: "ali-deepseek-v4-flash"
AI摘要时间: "2026-09-07T03:39:33.254Z"
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-minimax-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.

## MiniMax M3

The MiniMax-M3-MXFP8 model is the MXFP8 quantized variant of MiniMax M3, a native multimodal model with a one million token context. The model has about 428 billion total parameters with about 23 billion activated parameters and uses MiniMax Sparse Attention (MSA) for efficient long-context processing. This model is optimized for coding, long-horizon agentic workflows, and collaborative productivity tasks.

| Hugging Face Model ID | Model Capability | Minimum Dedicated AI Cluster Unit Shape |
| --- | --- | --- |
| [MiniMaxAI/MiniMax-M3-MXFP8](https://huggingface.co/MiniMaxAI/MiniMax-M3-MXFP8) | TEXT\_TO\_TEXT | - H200\_X8 - B200\_X8 |

## MiniMax M2

The MiniMax M2 text-to-text models are optimized for coding, complex reasoning, and agentic workflows such as tool use, search, and productivity tasks. MiniMax-M2 is a Mixture-of-Experts (MoE) model designed for efficient coding and agentic performance, and later MiniMax-M2 models extend this focus to more advanced software engineering and professional-work tasks. For more details, see MiniMax in the Hugging Face documentation.

| Hugging Face Model ID | Model Capability | Minimum Dedicated AI Cluster Unit Shape |
| --- | --- | --- |
| [MiniMaxAI/MiniMax-M2.7](https://huggingface.co/MiniMaxAI/MiniMax-M2.7) | TEXT\_TO\_TEXT |  |
| [MiniMaxAI/MiniMax-M2.5](https://huggingface.co/MiniMaxAI/MiniMax-M2.5) | TEXT\_TO\_TEXT |  |
| [MiniMaxAI/MiniMax-M2](https://huggingface.co/MiniMaxAI/MiniMax-M2) | TEXT\_TO\_TEXT |  |