@akshay_pachaar: Turn any PDF, image, DOCX, and PPTX into clean markdown. Parsing one PDF is easy. Parsing millions of them is where it …
Summary
Datalab has released Marker v2, an open-source document parsing pipeline that efficiently converts PDFs, images, DOCX, and PPTX files to markdown with support for over 90 languages and high performance on GPUs.
View Cached Full Text
Cached at: 08/23/26, 11:43 PM
Turn any PDF, image, DOCX, and PPTX into clean markdown.
Parsing one PDF is easy. Parsing millions of them is where it gets tricky.
Datalab just shipped Marker v2, a parsing pipeline that runs up to 23.7 pages/s on a single B200 GPU.
Supports 90+ languages.
100% open-source. https://t.co/JgfephJ3ki
Similar Articles
@HowToPrompt__: Someone open-sourced a tool that converts pdfs to markdown at 122 pages per second. → PDFs, DOCX, PPTX, XLSX, EPUB, ima…
An open-source tool converts PDFs, DOCX, PPTX, XLSX, EPUB, and images to markdown at 122 pages per second, supporting tables, equations, and forms on GPU, CPU, or Mac.
@opensourcelab9: To people who want to feed documents to AI A tool has been released that converts Word, PowerPoint, Excel, PDF, and EPUB…
A Rust-based open-source tool called anydoc has been released to convert Word, PowerPoint, Excel, PDF, and other document formats into Markdown for AI and LLM use, with bindings for Node.js and Python.
@VikParuchuri: Get marker here - https://github.com/datalab-to/marker… . Quickstart: pip install marker-pdf, then marker /path/to/fold…
Marker is an open-source tool that converts PDFs, images, and other document formats to markdown, JSON, chunks, and HTML quickly and accurately, with optional LLM enhancement.
@VikParuchuri: Marker 2 is out now - up to 5x faster and more accurate than mineru, docling, and liteparse with similar configs. Conve…
Marker 2 is released, offering up to 5x faster and more accurate conversion of PDFs, images, and DOCX to markdown compared to mineru, docling, and liteparse.
@VikParuchuri: Marker started as a small project to parse my PDFs. Today Datalab projects have 72k GitHub stars and 6M downloads a mon…
Vik Paruchuri announces that his PDF parsing tool Marker has grown into Datalab projects with 72k GitHub stars and 6M monthly downloads, and they are hiring a founding open-source engineer.