NVIDIA Releases Nemotron 3.5 Parse for Document Extraction

Oct 18, 2026
NVIDIA released Nemotron 3.5 Parse, a model that converts document images into structured text with layout classes, bounding boxes and reading order.

NVIDIA released Nemotron 3.5 Parse on Hugging Face on October 17. The model converts document images into structured text with semantic layout classes, bounding boxes and reading order; the benchmark results below come from NVIDIA's own testing.

Nemotron 3.5 Parse combines a C-RADIOv4-SO400M vision encoder with a 10 layer mBART decoder and has about 0.63 billion parameters. It supports tables and charts, uses a multilingual tokenizer with 72,505 tokens and processes scanned or rendered PDFs, slides, forms and reports.

NVIDIA reports a mean score of 75.20 on ParseBench, including 84.67 for tables and 64.40 for charts. It also reports 83.73 on the IndicVisionBench OCR test across 10 languages and 99.51 character bag F1 on the synthetic MOSCAR test. The model is available for commercial and noncommercial use under the OpenMDW License Agreement version 1.1.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.