Marker
An open-source tool that converts PDFs and other documents to Markdown, JSON and HTML.
These buttons open the developer's own site, repository or store listing in a new tab. wares.gg does not host downloads.
About Marker
Marker converts PDF, image, PPTX, DOCX, XLSX, HTML and EPUB files in any language into Markdown, JSON, chunks or HTML. It formats tables, forms, equations, inline math, links, references and code blocks. It also extracts images and strips headers, footers and similar clutter.
It runs locally on a GPU, a CPU or Apple MPS. It can optionally call an LLM to improve accuracy. Datalab also sells a hosted platform built on a newer model.
Strengths
- Handles tables, equations and code blocks
- Accepts many input formats besides PDF
- Runs locally on GPU, CPU or Apple MPS
- Actively developed
Limitations
- Model weights are under a separate licence from the code
- Needs a Python environment and benefits from a GPU
- Optional LLM mode depends on an external model
Details
- Pricing
- FreeThe code is free under Apache 2.0; model weights have a separate licence, and Datalab sells a paid hosted service.
- License
- Apache-2.0
- Developer
- Datalab
- Platforms
- Self-hosted, Command line
- How it runs
- Downloadable app, Self-hosted
- Account
- Not required
- Best suited for
- Turning PDFs into clean Markdown for notes, search or LLM pipelines
- Categories
- PDF tools, Developer tools
- Last verified
- Added
- Provenance
- Facts checked against the developer's own pages and store listings, 2 sources on file.
Alternatives to Marker
Compare allSoftware that can replace Marker for an important use case, and what changes if you switch.
MinerU
A document parser that converts PDFs, Office files and scans into Markdown and JSON.
MinerU converts PDFs, Office files and scans to Markdown and JSON with several local model backends, under a non-standard license.
MarkItDown
Python command-line tool that converts PDFs, Office files and other documents into Markdown.
MarkItDown is an MIT Python command-line tool converting PDFs and Office files to Markdown for LLMs, lighter weight but aimed less at high-fidelity conversion.
olmOCR
Open-source toolkit that uses a vision language model to turn PDFs and scans into Markdown.
olmOCR uses an open vision language model to convert PDFs and scans to Markdown with tables and handwriting, but requires a capable GPU on Linux.
PaddleOCR
OCR toolkit that turns PDFs and images into structured data.
PaddleOCR parses layout, tables and formulas into JSON and Markdown under Apache-2.0, built on the large PaddlePaddle framework.
Marker as an alternative
Listings that name Marker as an alternative.
pdf2htmlEX
A command-line converter that turns PDF files into HTML while keeping text and layout.
Marker converts PDFs to HTML, Markdown and JSON with tables and equations, but outputs clean structure rather than a visual copy of the layout.
Similar software
Related functionality, not necessarily a direct replacement.
Poppler
PDF rendering library with pdftotext, pdftoppm and pdfinfo tools.
Tesseract OCR
The open-source OCR engine behind most free text recognition tools.
EasyOCR
Python OCR library covering more than eighty languages out of the box.
PDFMathTranslate
An AI tool that translates scientific PDFs while keeping formulas, charts and layout intact.
ChatPDF
An AI tool that summarizes PDFs and answers questions about them, with citations to the source.
