# OpenBMB's MiniCPM-OCR 1.0 processes Anthropic's 415-page S-1 locally on a MacBook

> Original title: Huge thanks to @atomic_chat_hq for the awesome demo! 🙌

- Source: OpenBMB
- Published: 2026-10-28T13:19:46.000Z
- Bad Influence: https://badinfluence.news/items/jc326qrpvb45xmk78rwy8rjo6
- Original: https://x.com/OpenBMB/status/2115433341226745861

## Summary

MiniCPM-OCR 1.0 ran locally on an M5 Max MacBook to process all 415 pages of Anthropic's S-1 filing, according to Atomic Chat. The 1.2GB model took about 4 seconds per page, with no data leaving the device.

## Post

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. 🔥

## Quoted post @atomic_chat_hq

> 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

https://x.com/atomic_chat_hq/status/2115425911961223174