# NVIDIA releases Nemotron 3.5 Parse for document extraction

> NVIDIA released a small open model that turns document images into structured text with layout data, and teams should test it on their own documents before using it in production.

- Type: AI news
- Page: https://completeaitraining.com/news/nvidia-releases-nemotron-35-parse-for-document-extraction/
- Published: 2026-10-20
- Updated: 2026-10-20
- Author: Jeroen Erne
- Jobs: Creatives, Customer support, Education, Healthcare, Hospitality and events, Insurance, IT and development, Marketing, Operations, Product development, Sales, Science and research, Writers
- Reading time: 1 min

NVIDIA has released Nemotron 3.5 Parse, a compact open model designed to convert document images into structured text. The output includes layout classes, bounding boxes, and reading order, which can help teams process invoices, contracts, forms, and multilingual documents more systematically.

NVIDIA has published performance benchmarks for the model. Professionals in fields such as insurance, healthcare, legal operations, and finance should validate those results on their own document types before moving into production use. Testing against real-world samples is necessary to confirm accuracy on the specific layouts and languages an organization handles.

---

This is the Markdown form of https://completeaitraining.com/news/nvidia-releases-nemotron-35-parse-for-document-extraction/. The whole site is mapped at https://completeaitraining.com/llms.txt.