Suggestions appear as you type. Use the up and down arrows to choose one and Enter to open it.

This page's audience our own tag's counts — open to see them
–Visits
–Page views
–Clicks to vendors
–Time on page
–Reading now
Clicks to vendors, by tool
  • –
Top countries
  • –
Devices
  • –

– · visits, page views and clicks counted by our own tag, which counts more than our checked analytics; every figure rounded down · how we count

Nougat review

Free#44 of 60 in PDF Data Extraction Software

A free, open-source parser focused on converting scientific PDFs into markup.

5.0/10Editor score
Nougat5.0 Explore Nougat

Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026

Nougat is open-source software from Meta Platforms, Inc. that converts scientific PDFs into lightweight, Markdown-compatible markup saved as .mmd files. Its focus is researchers who need to extract academic document content, especially mathematics and tables, rather than users seeking a general-purpose PDF workflow. It can process an individual PDF or a directory of PDFs, and supports selecting pages for processing. Nougat is available as self-hosted software with a locally runnable prediction API; it is not presented as a priced hosted service.

Its central strength is handling academic content: Nougat parses LaTeX mathematics and tables alongside document text. Users can choose between small and base model checkpoints, and can run predictions through the command-line interface or start the optional local API for programmatic use. Directory processing suits workloads involving multiple PDFs, while page selection allows processing a chosen portion of a document. These capabilities make it a focused option for converting research papers into markup, not a substitute for tools aimed at arbitrary PDF types.

Nougat is free and open source, but its licenses have an important distinction: the codebase is MIT-licensed, while the model weights are licensed CC-BY-NC. Its documentation says it works best with English papers similar to arXiv and PMC papers used for training, so readers handling other languages or document styles should consider whether that fit is sufficient. Documentation and community are the listed support channels. Researchers comfortable running self-hosted software and working with academic PDFs should consider Nougat; those needing broader document coverage or a hosted service should look elsewhere.

Nougat pros and cons

  • Where it wins
    • Converts academic PDFs to Markdown-compatible .mmd files
    • Parses LaTeX mathematics and tables
    • Processes individual PDFs or directories, with page selection
  • Where it doesn't
    • Designed for scientific documents rather than broad PDF extraction
    • Works best with English papers similar to arXiv and PMC training papers
    • Model weights use a CC-BY-NC license

Nougat fact sheet, pricing and score →

Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.

Last updated · How we research and update