AIsaAIsaStudio 中文 Open AIsa Studio
Hugging Face 热门模型· Models·

openbmb releases MiniCPM-OCR 1.0, a 1.3B open-source OCR model

Original title: openbmb/MiniCPM-OCR-1.0 (image-text-to-text)

OpenBMB released MiniCPM-OCR 1.0, the first OCR-specific model in the MiniCPM-V/o family, a 1.3B open-source (Apache-2.0) model for text, table, formula, chart and seal understanding plus information extraction. It scores 93.68 on Real5-OmniDocBench and 54.7 on OCRBench v2, reaches 1.2 pages/s on an RTX 5090, with throughput about 1.49× PaddleOCR-VL-1.6 and 3.62× MinerU2.5 Pro, and DSpark decoding improving end-to-end efficiency by 55%. It ships with day-one support for vLLM, SGLang, llama.cpp and Ollama, plus quantized variants, a pip SDK, an API and online demos.

Why it matters

The README provides concrete scores across four benchmarks, throughput comparisons and deployment options, letting readers weigh it against existing OCR solutions.

Read the original ↗

The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.

Original article

Hugging Face 热门模型第 27 名：openbmb/MiniCPM-OCR-1.0，261 赞，近期下载 791 次。 标签：safetensors, minicpm_ocr, minicpm-ocr, ocr, document-parsing, multimodal, vision-language, table-recognition, formula-recognition, image-text-to-text, conversational, en

README：

GitHub · API · Official Demo · HF Spaces · Usage · DSpark · Skill

MiniCPM-OCR 1.0 (1.3B) is the first OCR-specific model in the MiniCPM-V/o family. It focuses on text-centric document understanding — text, tables, formulas, charts, seals, and structured information extraction — and balances quality against speed on real-world captures.

Highlights

  • 🏆 SOTA document parsing: 93.68 on Real5-OmniDocBench, a benchmark for real-world document parsing, with leading results on OmniDocBench v1.6, Wild-OmniDocBench, and olmOCR-Bench. Handles Chinese and English documents and PDFs, including scans, curved pages, photographs, skewed pages, and recaptured documents.
  • ⚡ Efficient inference. With DSpark decoding acceleration (BF16, GGUF) end-to-end processing efficiency improves by 55%. Throughput is about 1.49× PaddleOCR-VL-1.6 and 3.62× MinerU2.5 Pro.
  • 🔍 General recognition and information extraction: 54.7 on OCRBench v2, plus key information extraction (KIE) for downstream automation.
  • 🛠️ Easy to deploy and develop: vLLM, SGLang, llama.cpp, and Ollama from day one, with quantized variants and multi-chip builds. Supports further fine-tuning, and ships a pip SDK, a full API, and agent workflows. Online demos: HF Spaces · CN · Official CN · Official Global.

SOTA quality at higher throughput

Among the open-source OCR models compared, MiniCPM-OCR 1.0 reaches 1.2 pages/s and the highest equal-weight average score across OmniDocBench v1.6, Real5-OmniDocBench, Wild-OmniDocBench, and olmOCR-Bench.

Average score is the equal-weight mean of the four benchmarks. All models use accelerated configurations. Settings and reproduction: reproduction guide. Per-model throughput: model guide.

Benchmark comparisons

Full MiniCPM-OCR 1.0 evaluation results

Each panel keeps its own benchmark's scores; higher is better. Scores from different benchmarks are not directly comparable. Test settings and reproduction steps are in the reproduction guide; per-benchmark discussion is in the model guide.

Throughput

On an NVIDIA GeForce RTX 5090 with all 1651 OmniDocBench v1.6 images, image-level concurrency 1, and each system's accelerated configuration, MiniCPM-OCR 1.0 reaches 1.2 pages/s (relative throughput 1.00×; higher is faster).

Concurrency 1 is image-level: regions inside a page are still recognised in parallel. Real throughput also depends on page content, backend, concurrency, and hardware.

Examples

Left to right: original document, detected layout, and rendered Markdown.

English documents

Chinese documents

More examples

The original belongs to Hugging Face 热门模型 and its authors and is reproduced here for reading. To have it removed, write to support@aisa.one.