{
  "contentStorage": "postgres",
  "title": "Llama 4 Maverick",
  "description": "Llama 4 Maverick 是 Meta 于 2025 年 4 月 5 日发布的 Llama 4 家族通用旗舰多模态模型。",
  "url": "/ar/works/llama-4-maverick.html",
  "entity": {
    "id": "work_llama_4_maverick",
    "type": "work",
    "title": "Llama 4 Maverick",
    "slug": "llama-4-maverick",
    "aliases": [
      "Llama-4-Maverick-17B-128E-Instruct"
    ],
    "summary": "Llama 4 Maverick 是 Meta 于 2025 年 4 月 5 日发布的 Llama 4 家族通用旗舰多模态模型。",
    "status": "published",
    "categories": [
      "category-science-technology"
    ],
    "tags": [],
    "sources": [
      {
        "id": "s1",
        "title": "The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation",
        "url": "https://ai.meta.com/blog/llama-4-multimodal-intelligence/"
      },
      {
        "id": "s2",
        "title": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 · Hugging Face",
        "url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
      },
      {
        "id": "s3",
        "title": "Llama 4 Maverick 17B Instruct - Amazon Bedrock",
        "url": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.html"
      },
      {
        "id": "s4",
        "title": "Llama 4, reviewed",
        "url": "https://benchr.org/articles/llama-4-review"
      }
    ],
    "createdAt": "2026-11-10T15:06:23+08:00",
    "updatedAt": "2026-11-10T15:06:23+08:00",
    "updatedBy": "user:admin",
    "revision": 1,
    "body": "Llama 4 Maverick 是 Meta 于 2025 年 4 月 5 日发布的 Llama 4 家族通用旗舰多模态模型。[^s1]\n\n## 发布背景\n发布时上下文窗口为1M tokens，Hugging Face 模型标识为 meta-llama/Llama-4-Maverick-17B-128E-Instruct。[^s1]\nMoE 架构：17B 激活参数、400B 总参数、128 位专家，上下文 1M tokens；原生多模态，文本与图像输入、文本与代码输出，约 22T tokens 预训练、知识截止 2024 年 8 月。[^s1]\n\n## 定价与获取\n开源权重（非 OSI 开源许可），按 Llama 4 Community License 发布，提供 BF16 与 FP8 权重；Meta 无官方统一 API 定价，第三方托管价格因服务商而异，故定价填 null，最大输出亦因托管方而异，未采用单一数值。[^s1]\n\n## 性能表现\n以下为Meta公布的自家评测结果，尚未经独立复现。[^s1]\n- MMLU Pro：80.5（（指令微调版）：高于 Llama 4 Scout 74.3、Llama 3.1 405B 73.4）[^s1]\n- GPQA Diamond：69.8（（指令微调版）：高于 Llama 4 Scout 57.2、GPT-4o 53.6）[^s1]\n- MMMU：73.4（（指令微调版）：高于 Llama 4 Scout 69.4、Gemini 2.0 Flash 71.7、GPT-4o 69.1）[^s1]\n- LiveCodeBench：43.4（（指令微调版）：高于 Llama 4 Scout 32.8、GPT-4o 32.3）[^s1]\n\n## 主要特点\n- 与 Scout 同日发布，Scout 为 17B 激活/109B 总参数、16 专家、10M 上下文的同门轻量版；Maverick 由未公开发布的教师模型 Behemoth（288B 激活、约 2T 总参数）蒸馏/协同蒸馏而来；发布时引用的 LMArena 1417 分来自实验性聊天变体 Llama-4-Maverick-03-26-Experimental，并非公开权重。[^s1]\n\n## 定位与后续\nLlama 4 家族的通用旗舰多模态 MoE，接替 Llama 3.3 70B / Llama 3.1 405B 的开放权重旗舰位置；原定的更大后继 Behemoth 未公开发布，2026 年 4 月 Meta 已将新旗舰转向闭源 Muse Spark，Maverick 仍是可公开获取的最高档 Llama 4。 其前代为[[work_llama_3_3|Llama 3.3]]。[^s1]",
    "url": "/works/llama-4-maverick.html",
    "lang": "ar",
    "sourceLang": "zh",
    "fallback": true,
    "availableLangs": [
      "zh"
    ],
    "workKind": "ai_model"
  },
  "entities": null,
  "relations": [
    {
      "id": "relation_work_llama_4_maverick_published_by_meta",
      "fromId": "work_llama_4_maverick",
      "relationType": "published_by",
      "toId": "organization_meta",
      "sourceRefs": [
        {
          "entityId": "work_llama_4_maverick",
          "sourceId": "s1"
        }
      ],
      "label": "Published by",
      "targetId": "organization_meta",
      "targetTitle": "Meta",
      "targetUrl": "/ar/organizations/meta.html",
      "incoming": false
    }
  ],
  "versions": [
    {
      "revision": 1,
      "updatedAt": "2026-11-10T15:06:23+08:00",
      "message": "当前版本",
      "hasSnapshot": true,
      "url": "/ar/works/llama-4-maverick/at/1.html"
    }
  ],
  "lang": "ar",
  "availableLangs": [
    "zh"
  ],
  "fallback": true,
  "infoFields": [
    {
      "key": "work_kind",
      "label": "Work kind",
      "value": "نموذج ذكاء اصطناعي"
    }
  ],
  "relationsTotal": 1,
  "relationCounts": [
    {
      "relationType": "published_by",
      "incoming": false,
      "label": "Published by",
      "total": 1
    }
  ]
}