marker vs MinerU
Datalab's 39k-star PDF-to-Markdown/JSON converter: a layout pipeline plus an optional LLM pass for tables, forms and equations, with chunk output and form-value extraction built in. — versus — Heavyweight document-to-markdown/JSON parser — PDFs plus Office (docx/pptx/xlsx) through layout analysis and OCR into LLM-ready output for RAG and agentic pipelines. 73k stars, self-hostable.
Both convert PDF and Office files to LLM-ready Markdown/JSON. MinerU casts the wider format and pipeline net; marker is leaner to install, faster per page, and pushes hard blocks to an LLM of your choosing.
| marker | MinerU | |
|---|---|---|
| Stars | 39k | 78k |
| Forks | 2.8k | 6.6k |
| Language | Python | Python |
| License | Apache-2.0 | NOASSERTION |
| Last activity | 17 days ago | today |
| Topics | ocr, rag | ocr, rag |
| Curated connections | 7 | 13 |
marker — the curator's take
The default answer when you need a lot of documents turned into clean Markdown on your own hardware: fast per page, tuned by people who do this for a living, and it can call Gemini/Claude/OpenAI-compatible/Ollama models only on the blocks that need help. Two caveats before you ship it: the code is Apache-2.0 but the model weights are OpenRAIL-M (free for research, personal use and companies under $5M funding/revenue), and on genuinely nasty input — scans, handwriting, dense multi-column tables — Datalab's own VLM chandra beats it. Born-digital corpus and no appetite for model calls? Use a deterministic parser instead.
MinerU — the curator's take
The incumbent when document variety is the problem: beyond PDFs it handles Office formats, with mature layout analysis (reading order, tables, formulas) and a huge user base shaking out edge cases. NOT the lightest option — it's a full pipeline with model downloads and real hardware appetite; for a handful of clean PDFs a smaller tool is faster to stand up. Check the license (NOASSERTION on GitHub — AGPL-family, matters for commercial use).