阿里巴巴 MNN 团队发布了 MNN-Pocket-0.3B，这是一个紧凑的 173MB 设备端语言模型，专为移动应用设计。该模型能够在 iPhone 18 Pro 等设备上离线解码，速度约为每秒 350 个 token。此次发布旨在促进 AI 功能直接集成到移动应用中。 AI
影响 使更多 AI 功能可以直接在移动设备上运行，提高性能和隐私。
排序理由 公司研究团队发布开源模型。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
淘宝 MNN 团队开源小型设备端语言模型
本文如何被排名
- Signal score
- 43 / 100
- Composite score across the factors below. Higher = stronger signal that this story matters right now.
- Newsworthiness bucket
- Research
- 公司研究团队发布开源模型。
- Source corroboration
- 2 independent sources
- Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
- Topics
- model release, product
- Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
- AI-industry relevance
- High
- Clearly on-topic for AI-industry coverage.
- Story freshness
- Breaking (< 6h)
- Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.
完整方法见我们的编辑标准。
报道来源 [2]
-
淘宝MNN团队开源MNN-Pocket-0.3B，一款专为手机App打造的173MB端侧模型
Alibaba's MNN team at Taobao open-sourced MNN-Pocket-0.3B, a 173MB INT4 on-device model it says decodes about 350 tokens per second offline on an iPhone 18 Pro.
-
淘宝MNN团队开源MNN-Pocket-0.3B，一个173MB的设备端语言模型，专为移动应用设计。来源：Pandaily https://pandaily.com/taobao-mnn
Taobao's MNN team has open-sourced MNN-Pocket-0.3B, a 173MB on-device language model designed for mobile apps. Source: Pandaily https:// pandaily.com/taobao-mnn-pocket -0-3b-open-source-on-device-small-language-model-phone-apps # AI