OpenBMB· @OpenBMB · X·· 4 小时前AI 评分55
AI 导读
OpenBMB 转发并感谢 @atomic_chat_hq 的演示：该演示在 M5 Max MacBook 上本地运行 MiniCPM-OCR 1.0，处理 Anthropic S-1 文件全部 415 页，1.2GB 模型约每页 4 秒，数据全程不离开设备。GGUF 权重已发布在 huggingface.co/AtomicChat/MiniCPM-OCR-1.0-GGUF。
正文 · 原文
Huge thanks to @atomic_chat_hq for the awesome demo! 🙌
They ran MiniCPM-OCR 1.0 locally on an M5 Max MacBook to process all 415 pages of Anthropic’s S-1 filing — with a 1.2GB model, ~4 seconds per page, and zero data leaving the device.
Small model, serious document understanding, fully local. 🔥
A 1.2GB model on a Mac read Anthropic's whole IPO 📄 @OpenBMB MiniCPM-OCR 1.0 went through all 415 pages of Anthropic's S-1 on an M5 Max MacBook at about 4 seconds a page and nothing ever left the laptop GGUFs -> https://huggingface.co/AtomicChat/MiniCPM-OCR-1.0-GGUF在 X 查看被引用的帖子
来源：OpenBMB · x.com