SmolDocling vs MiniCPM-V 4.5
Pick MiniCPM-V 4.5 for most real work: it is an Apache-2.0 8B model that runs on llama.cpp and vLLM with int4, GGUF and AWQ builds, and its authors claim strong OCRBench and OmniDocBench results. Pick SmolDocling only if you need bounding boxes or structured output (DocTags, HTML, LaTeX) from a 256M model and can accept a preview release that is English only and can loop on some pages.
SmolDoclinghuggingface/smoldocling | MiniCPM-V 4.5openbmb/minicpm-v | |
|---|---|---|
| Type | Open source | Vision model |
| Price | 1 credit / page | 2 credits / page |
| Per 1,000 pages | $1.00 | $2.00 |
| Typical speed | 1.0 s / page | 2.5 s / page |
| Best for | Very cheap page conversion | OCR on edge devices |
| Inputs | PDF, images | images |
| Languages | Mainly English | 30+ languages |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | ✓ Yes |
| Math | ✓ Yes | No |
| Bounding boxes | ✓ Yes | No |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | No | ✓ Yes |
| 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 SmolDocling if
- It outputs DocTags, Markdown, HTML, JSON, LaTeX and bounding boxes, so you get location tags for text, tables, code, formulas and charts.
- At 256M parameters it fits modest hardware, and it runs at about 0.35 seconds per page on an A100 with vLLM.
- It publishes scores you can check: TEDS structure 0.82 on FinTabNet at 150dpi, full-page OCR F1 0.80 and OCRBench 338.
Choose MiniCPM-V 4.5 if
- It is a general 8.7B VLM with Apache-2.0 weights and code, and it can answer questions about a document as well as read it.
- It has int4, GGUF and AWQ builds and runs on llama.cpp and vLLM, which suits on-device OCR and local document Q&A on a single GPU.
- It is not limited to English by anything in its published notes, while SmolDocling is English only and its authors point users to Granite-Docling for support.
Key differences
| SmolDocling | MiniCPM-V 4.5 | |
|---|---|---|
| Licence | Apache-2.0 per the model summary (the metadata tag says CDLA-Permissive-2.0) | Apache-2.0 for weights and code |
| Size | 256M parameters | 8.7B parameters, built on Qwen3-8B and SigLIP2-400M |
| How you run it | Self-hosted, you pay for compute | Self-hosted with llama.cpp, vLLM or Transformers, you pay for compute. Ollama and SGLang support were still pending on the model card |
| Output formats | DocTags, Markdown, HTML, JSON, LaTeX, bounding boxes | Plain text, Markdown, JSON. No bounding box or layout output |
| Published benchmarks | TEDS 0.82 (FinTabNet), full-page OCR F1 0.80, OCRBench 338 | Claims lead on OCRBench and state of the art PDF parsing on OmniDocBench, but the card shows scores only as images, so numbers are hard to verify |
| Languages | English only | Not published |
| Known failure | Endless token repetition and missing closing tags; Docling issue #1515 reports loops that make generation very slow even on sparse pages | No int4 VRAM figure published |
| Status | Preview release, superseded by Granite-Docling | Current 4.5 release |
Sources
- SmolDocling model card
- Docling issue #1515
- Granite-Docling comparison table
- Hugging Face model card
- MiniCPM-V 4.5 paper
What each one is
SmolDocling
Tiny 256M vision model from Hugging Face and IBM that outputs DocTags. Predecessor of Granite Docling.
SmolDocling detailsMiniCPM-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 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": "huggingface/smoldocling","fallbacks": ["openbmb/minicpm-v"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
SmolDocling alternativesMiniCPM-V 4.5 alternativesBest OCR models in 2026