OpenBMB 发布 MiniCPM-OCR 1.0 与校验模型 Jev，可本地跑在 iPhone
OpenBMB 把 1B 的 OCR 模型跑在了 iPhone 上，手写笔记、公式、模糊扫描件都能解析，还有个 2B 小模型帮你检查结果对不对，权重全开。
OpenBMB 推出 1B 规模的 MiniCPM-OCR 1.0，在 Real5-OmniDocBench 得 93.68、OCRBench v2 得 54.7，主打小体积下的文档解析速度与精度。配套的 2B 决策模型 MiniCPM-OCR Jev 在 JevOCRBench 上接近 Qwen3.5-397B-A17B，负责给 OCR 结果打 0-1 分并标记需人工复核的内容。两者都开放权重，支持 llama.cpp、vLLM、SGLang、Ollama 部署，演示中直接在 iPhone Duo 和 iPad 上本地运行。
🎬 MiniCPM-OCR in action — running locally on iPhone Duo and iPad. Parse fast and accurately. Guard the results. All in your hands. 🙌
Handwritten notes, complex formulas, newspapers, poor-quality scans—real documents put OCR to the test.
📄 MiniCPM-OCR 1.0 — SOTA OCR performance and speed at 1B scale. It achieves 93.68 on Real5-OmniDocBench and 54.7 on OCRBench v2, combining accurate document parsing with efficient inference.
🛡️ MiniCPM-OCR Jev — A 2B decision model that checks OCR accuracy. It approaches Qwen3.5-397B-A17B on JevOCRBench and works with outputs from different OCR parsers.
Watch it compare parsed text, formulas, and tables with the original image and assign 0–1 correctness scores—helping you pick better results and identify what needs human review.
🔓 Open weights. Deploy your way. Run with llama.cpp, vLLM, SGLang, or Ollama. Customize with open-source fine-tuning code.
Watch it in action. 👇
🔗 GitHub: https://t.co/2SlATAJk08 🤗 Hugging Face: https://t.co/Ttq31GL8eJ 👉 Try the Demo：https://t.co/QsFAJT3AFy Use the API：https://t.co/dP01jBS2j2
