OCRRouter

SmolDocling vs InternVL3.5

Pick SmolDocling only for small English experiments where a 256M model and DocTags output matter, and note that it is a preview release superseded by Granite-Docling. Pick InternVL3.5 for document question answering and for teams that want one open model family at several sizes, from 1B to 241B-A28B. The main split is that SmolDocling is a narrow page converter with layout tags, while InternVL3.5 is a general vision language model with no bounding boxes by default.

SmolDoclinghuggingface/smoldoclingInternVL3.5opengvlab/internvl
TypeOpen sourceVision model
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed1.0 s / page3.0 s / page
Best forVery cheap page conversionSelf-hosted document understanding
InputsPDF, imagesimages
LanguagesMainly EnglishMultilingual
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 SmolDocling if

  • It outputs DocTags, Markdown, HTML, JSON, LaTeX and bounding boxes, so you get layout and location data for each element.
  • At 256M parameters it runs on modest hardware, and the authors report about 0.35 seconds per page on an A100 with vLLM.
  • One model covers text, tables (OTSL), code, formulas and charts with location tags, for English page conversion on a low budget.

Choose InternVL3.5 if

  • Nine sizes from 1B to 241B let you trade accuracy for cost, and the MoE variants 20B-A4B and 30B-A3B activate few parameters per token.
  • It suits document question answering and self-hosted multimodal pipelines, since it is a general vision language model.
  • Apache-2.0 licence, and models up to 30B fit on a single A100 per the model card.

Key differences

SmolDoclingInternVL3.5
Model typeDocument conversion VLM that outputs DocTags for DoclingGeneral open-weight vision language model family from OpenGVLab
Size256M parameters1B to 241B-A28B; the 8B variant is 8.5B
LicenceApache-2.0 per the model summary (the metadata tag says CDLA-Permissive-2.0)Apache-2.0
Output formatsDocTags, Markdown, HTML, JSON, LaTeX, bounding boxesPlain text, Markdown, JSON; no bounding boxes or layout output by default
BenchmarksTEDS structure on FinTabNet 0.82, full-page OCR F1 0.80, OCRBench 338Not published as text; the model card shows OCR scores only as chart images
LanguagesEnglish onlyNot published
Known failure or statusPreview release. Output can loop on some images (Docling issue #1515) and the paper lists endless token repetition and missing closing tags. Granite-Docling scores higher, e.g. TEDS 0.97 vs 0.82.The largest 241B-A28B model needs eight A100 GPUs, and the 38B model needs two A100s with tensor parallelism

Sources

What each one is

SmolDocling

Tiny 256M vision model from Hugging Face and IBM that outputs DocTags. Predecessor of Granite Docling.

SmolDocling 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": "huggingface/smoldocling","fallbacks": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

SmolDocling alternativesInternVL3.5 alternativesBest OCR models in 2026