No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from openbmb/MiniCPM-OCR-1.0
All models by openbmb →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.
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.
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.
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.
Left to right: original document, detected layout, and rendered Markdown.
English documents
Chinese documents
Original documents and parsed results, side by side.
English documents
Chinese documents
See the model guide for architecture, parsing workflow, deployment options, and benchmark breakdowns.
To quickly try text-centric document understanding and structured information extraction, we recommend HF Spaces, CN, Official CN, Official Global / API.
For local deployment of MiniCPM-OCR, we recommend our SDK (tutorial) with DSpark enabled by default. For document parsing task, It reads a PDF or image, detects layout with PP-DocLayoutV3, recognises each region, and assembles Markdown in reading order. Our SDK supports different inference backends, including vLLM, SGLang, llama.cpp, Ollama, Transformers, and FlagOS.
You can also have a coding agent follow the Agent Skill to set up the environment, download the model, and parse a first document.
LLaMA-Factory · ms-swift — data preparation, full-parameter SFT with the multimodal projector frozen, training, and evaluation (French handwritten text lines).
DSpark requires a matching main and draft model from the same release — do not mix draft weights with a different main checkpoint. See DSpark acceleration.
For OCR quality assessment (auto-accept, human-review routing, best-of-N across models), see MiniCPM-OCR Jev.
Installation, model downloads, GPU memory, input formats, and unexpected outputs: FAQ.
Model weights, code, and documentation are released under the Apache License 2.0.
Read and execute https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/SKILL_en.md