OCRRouter

Granite Docling vs InternVL3.5

Pick Granite Docling for English PDFs with tables, code and equations, especially inside a Docling pipeline on CPU or a small GPU. Pick InternVL3.5 for document question answering or when you want one model family you can scale from 1B to 241B. The main split is output: Granite Docling returns structured DocTags with bounding boxes, while InternVL3.5 returns plain text, Markdown or JSON with no layout by default.

Granite Doclingibm/granite-doclingInternVL3.5opengvlab/internvl
TypeOpen sourceVision model
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed1.5 s / page3.0 s / page
Best forSmall-model document conversionSelf-hosted document understanding
InputsPDF, imagesimages
LanguagesEnglish, experimental CJK and ArabicMultilingual
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
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

  • Its 258M parameters keep conversion cheap on CPU or a small GPU.
  • It outputs DocTags, Markdown, HTML, LaTeX and bounding boxes, so layout and coordinates are available.
  • The model card reports table structure TEDS of 0.97 on FinTabNet, equation F1 of 0.968 and code recognition F1 of 0.988.

Choose InternVL3.5 if

  • It comes in nine sizes from 1B to 241B-A28B, so you can trade accuracy for cost within one family.
  • It suits document question answering and wider multimodal pipelines, not only page conversion.
  • Models up to 30B run on a single A100, and the 20B-A4B and 30B-A3B MoE variants activate few parameters per token.

Key differences

Granite DoclingInternVL3.5
LicenceApache-2.0Apache-2.0, built on Apache-2.0 Qwen3
Size258M parameters1B to 241B-A28B; the 8B variant is 8.5B
Output formatsDocTags, Markdown, HTML, LaTeX, bounding boxesPlain text, Markdown, JSON; no bounding boxes or layout output by default
Published OCR benchmarksFull-page OCR F1 0.84, OCRBench 500, table TEDS 0.97 (FinTabNet), all from the model cardNot published as text; the model card shows OCR scores only as chart images
LanguagesEnglish primary; Japanese, Arabic and Chinese are marked experimentalNot published
HardwareRuns on CPU or a small GPU; T4-class GPUs without bfloat16 may output only exclamation marks unless run in float32Up to 30B on one A100, 38B on two A100s, 241B-A28B on eight A100s
Known failureCan get stuck in repetitive loops on page headings and invoices; vLLM can fail with a wte attribute error unless you use the untied revisionLarger sizes are impractical on CPU-only setups; no word coordinates

Sources

What each one is

Granite Docling

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

Granite Docling details

InternVL3.5

Shanghai AI Lab's open vision-language family (1B to 241B, August 2025), strong on OCR and document benchmarks.

InternVL3.5 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": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Granite Docling alternativesInternVL3.5 alternativesBest OCR models in 2026