OpenBMB 开源 MiniCPM-OCR 套件：1B 识别模型加 2B 质检模型
OpenBMB 出了套开源 OCR，1B 小模型跑得比 PaddleOCR-VL 快 1.49 倍，还带个 2B 模型专门检查识别结果错没错，表单识别可靠性党可以看看。
OpenBMB 发布开源 MiniCPM-OCR 套件，含两个模型。MiniCPM-OCR 1.0 是 1B 规模识别模型，在 Real5-OmniDocBench 得 93.68 分、OCRBench v2 得 54.7 分，速度为 PaddleOCR-VL-1.6 的 1.49 倍、MinerU2.5 Pro 的 3.62 倍。MiniCPM-OCR Jev 是 2B 质检模型，用于核查各 OCR 引擎输出的文本、公式和表格，在 JevOCRBench 得 93.6 分，超过 JEV-35B-A3B 的 90.1 分，接近 Qwen3.5-397B-A17B 的 93.8 分。搭配 DSpark 和 SDK 并发优化后吞吐可达每分钟 128 页，支持 vLLM、SGLang、llama.cpp、Ollama 部署，并通过 FlagOS 适配 14 家芯片厂商。
Your OCR says it’s done—but did it get everything right? 🤔 In high-stakes workflows, even a small error can be costly.
🚀 Meet the MiniCPM-OCR suite: an open-source solution to parse fast and guard the results.
Two new models: 🔹 MiniCPM-OCR 1.0 — SOTA OCR performance and speed at 1B scale. Compact, accurate, and fast. 🔹 MiniCPM-OCR Jev — A 2B decision model that helps assess parsing accuracy, with performance approaching that of Qwen3.5-397B-A17B on JevOCRBench.
⚡ What’s new? Small model, SOTA results: MiniCPM-OCR 1.0 scores 93.68 on Real5-OmniDocBench and 54.7 on OCRBench v2.
A sharp goalkeeper 🛡️: MiniCPM-OCR Jev is model-agnostic, checking text, formulas, and tables from different OCR parsers. It achieves 93.6 on JevOCRBench, outperforming JEV-35B-A3B (90.1) and approaching Qwen3.5-397B-A17B (93.8).
Up to 128 pages per minute 🤯: With DSpark, MiniCPM-OCR runs at 1.49× the speed of PaddleOCR-VL-1.6 and 3.62× that of MinerU2.5 Pro. The SDK’s concurrency optimizations further boost throughput to as much as 128 pages per minute.
Deploy where you work: Day-0 support for Arm, Houmo AI, Intel, and NVIDIA, plus 10 more chip vendors through FlagOS.
Ready for your stack: vLLM, SGLang, llama.cpp, and Ollama, with quantized models, fine-tuning support, and Agent Skills.
🔗 GitHub: https://t.co/2SlATAJk08 🤗 Hugging Face: MiniCPM-OCR 1.0：https://t.co/i347di4Fju MiniCPM-OCR Jev：https://t.co/ayVzhCJenh 👉 Try the Demo：https://t.co/QsFAJT3AFy Use the API：https://t.co/dP01jBS2j2
- rohanpaul_ai16:41原文
