OCRRouter

Granite Docling vs MiniCPM-V 4.5

Pick Granite Docling for English PDFs with tables, code and equations, especially inside a Docling pipeline on CPU or a small GPU. It is only 258M parameters and outputs DocTags with bounding boxes. Pick MiniCPM-V 4.5 when you need a general 8.7B vision language model for on-device OCR or local document Q&A, and do not need coordinates.

Granite Doclingibm/granite-doclingMiniCPM-V 4.5openbmb/minicpm-v
TypeOpen sourceVision model
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed1.5 s / page2.5 s / page
Best forSmall-model document conversionOCR on edge devices
InputsPDF, imagesimages
LanguagesEnglish, experimental CJK and Arabic30+ languages
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNo✓ Yes
Math✓ YesNo
Bounding boxes✓ YesNo
ConfidenceNoNo
FormsNoNo
MultilingualNo✓ Yes
On OCRRouterAvailableAvailable

Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.

Which to choose

Choose Granite Docling if

  • You run a Docling pipeline: it outputs DocTags, Markdown, HTML, LaTeX and bounding boxes.
  • Your documents are English PDFs with tables, code and equations: table structure TEDS is 0.97 on FinTabNet, code F1 is 0.988 and equation F1 is 0.968, per the model card.
  • You want low-cost conversion on CPU or a small GPU, since the model has only 258M parameters.

Choose MiniCPM-V 4.5 if

  • You need a general vision language model that also answers questions about a document, run locally on a single GPU.
  • You want quantized deployment on edge devices: int4, GGUF and AWQ builds run on llama.cpp and vLLM.
  • Your documents are not English-first, and you want to avoid Granite Docling's experimental status for Japanese, Arabic and Chinese.

Key differences

Granite DoclingMiniCPM-V 4.5
Size258M parameters8.7B parameters, built on Qwen3-8B and SigLIP2-400M
LicenceApache-2.0Apache-2.0 weights and code
How you run itSelf-hosted, typically inside DoclingSelf-hosted with llama.cpp, vLLM, Ollama or Transformers; Ollama and SGLang support were still pending on the model card
Output formatsDocTags, Markdown, HTML, LaTeX, bounding boxesPlain text, Markdown, JSON; no bounding box or layout output
Published benchmarksTable TEDS 0.97 (FinTabNet), full-page OCR F1 0.84, equation F1 0.968, OCRBench 500, all from the authorsNot published as numbers; the model card shows scores only as images. OpenBMB claims leading OCRBench results and state of the art PDF parsing among general MLLMs on OmniDocBench
LanguagesEnglish primary; Japanese, Arabic and Chinese marked experimentalNot published
Known failure modesRepetitive loops on page headings and invoices; exclamation-mark output on GPUs without bfloat16 such as T4 unless run in float32; vLLM wte attribute error needs the untied revision; Ollama FP16 overflow hallucinations on CPUNo int4 VRAM figure published; benchmark numbers hard to verify

Sources

What each one is

Granite Docling

Compact IBM vision model that converts pages to DocTags for the Docling pipeline.

Granite Docling details

MiniCPM-V 4.5

8B vision model from OpenBMB (August 2025) built to run on devices, with strong OCR and document parsing.

MiniCPM-V 4.5 details

Try both on your own file

Run the file once with each model and compare the output.

PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?

Use one, fall back to the other

{"model": "ibm/granite-docling","fallbacks": ["openbmb/minicpm-v"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Granite Docling alternativesMiniCPM-V 4.5 alternativesBest OCR models in 2026