MinerU vs Granite Docling
Pick MinerU for mixed corpora of PDFs and Office files, and for Chinese and English academic papers, where you need many output formats and can accept a custom licence. Pick Granite Docling for English PDFs with tables, code and equations, where Apache-2.0 and a 258M model that runs inside Docling matter most. The main split is scope: MinerU is a wide toolkit with licence strings attached, Granite Docling is a small, permissively licensed model that is weak outside English.
MinerUopendatalab/mineru | Granite Doclingibm/granite-docling | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 1 credit / page |
| Per 1,000 pages | $2.00 | $1.00 |
| Typical speed | 2.0 s / page | 1.5 s / page |
| Best for | Academic PDFs | Small-model document conversion |
| Inputs | PDF, images | PDF, images |
| Languages | 80+ languages | English, experimental CJK and Arabic |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | No |
| On OCRRouter | Available | Available |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
Which to choose
Choose MinerU if
- It accepts PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML in one tool, so mixed Office and PDF corpora need no extra converters.
- It handles Chinese and English academic papers, while Granite Docling marks Chinese, Japanese and Arabic as experimental.
- Its basic ONNX tier runs on CPU with about 2 GB RAM, so you can start batch conversion without a GPU.
Choose Granite Docling if
- It is Apache-2.0 licensed, while MinerU uses a custom licence and its 1.2B VLM weights are tagged AGPL-3.0.
- At 258M parameters it suits low-cost CPU or small GPU conversion of English PDFs with tables, code and equations.
- It reports table structure TEDS 0.97 on FinTabNet, code F1 0.988 and equation F1 0.968, and it fits directly into Docling pipelines.
Key differences
| MinerU | Granite Docling | |
|---|---|---|
| Licence | MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0 | Apache-2.0 |
| Model size | MinerU2.5 VLM: 1.2B parameters | 258M parameters |
| Input formats | PDF, images, DOCX, PPTX, XLSX, EPUB, OFD, HTML | Not published |
| Output formats | Markdown, HTML, LaTeX, DOCX, EPUB, JSON | DocTags, Markdown, HTML, LaTeX, bounding boxes |
| Languages | Chinese and English academic papers are a listed strength | English primary; Japanese, Arabic and Chinese experimental |
| Hardware | Basic tier: CPU with 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAM | Runs on CPU or small GPU; on GPUs without bfloat16 such as T4 it may output only exclamation marks unless run in float32 |
| Known failure | VLM tiers drop merged header rows in tables such as bank statement account lines; repeated content can produce 300 KB figure blocks | Gets stuck in repetitive loops on page headings and invoices |
Sources
- MinerU GitHub README
- MinerU2.5 model card
- Issue #5554 table header rows
- Granite-Docling model card
- HF discussion #24 repetition
What each one is
MinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU detailsGranite Docling
Compact IBM vision model that converts pages to DocTags for the Docling pipeline.
Granite Docling detailsTry both on your own file
Run the file once with each model and compare the output.
Use one, fall back to the other
{"model": "opendatalab/mineru","fallbacks": ["ibm/granite-docling"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
MinerU alternativesGranite Docling alternativesBest OCR models in 2026