# NVIDIA's Nemotron 3.5 Parse Targets Document OCR

> A new vision-language model from NVIDIA is tuned specifically for reading and structuring documents rather than general chat.

Published by The Open Weights on Sep 3, 2026. Canonical: https://theopenweights.com/news/nemotron-3-5-parse-4kv5

## Key facts

- Company: NVIDIA
- Model: Nemotron 3.5 Parse
- Version: 3.5 Parse
- Category: Vision-Language
- Modalities: Vision-Language
- License: Other (Open weights, commercial use allowed)
- Context window: 16K tokens
- Architecture: RadioMBartPrefixForCausalLM
- Precision: FP32
- Weights size: 2.5 GB
- Significance: notable
- Published: 2026-09-03
- Last verified: 2026-10-25
- Hugging Face: https://huggingface.co/nvidia/Nemotron-3.5-Parse
- Canonical URL: https://theopenweights.com/news/nemotron-3-5-parse-4kv5

NVIDIA has published **Nemotron 3.5 Parse**, a vision-language model built for a focused job: reading documents and turning their visual layout into structured, machine-usable text. The model is [available on Hugging Face](https://huggingface.co/nvidia/Nemotron-3.5-Parse) under a custom NVIDIA license.

Unlike general-purpose multimodal chat models, this release is positioned squarely around optical character recognition and document parsing. That makes it a tool for extracting text, tables, and layout from scanned pages, PDFs, and images rather than for open-ended conversation.

## Why it matters

Document understanding is one of the most practical and commercially valuable corners of the AI stack. Enterprises process invoices, forms, contracts, and reports at scale, and accurate parsing is often the bottleneck before any downstream automation can happen.

- Specialized for OCR and structured document extraction
- Vision-language architecture, so it reasons over page layout as well as text
- Distributed openly on Hugging Face for developers to test and integrate

By releasing a parsing-focused model under the Nemotron banner, NVIDIA is extending its family into a niche where precision matters more than breadth. Teams evaluating it should check the license terms and run their own benchmarks against existing OCR pipelines, since NVIDIA has not published detailed parameter counts or context specifications with this initial listing.

## Get the model

- [Hugging Face](https://huggingface.co/nvidia/Nemotron-3.5-Parse)

## Sources

- [nvidia/Nemotron-3.5-Parse](https://huggingface.co/nvidia/Nemotron-3.5-Parse) — Hugging Face, Sep 3, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "NVIDIA's Nemotron 3.5 Parse Targets Document OCR", The Open Weights, Sep 3, 2026, https://theopenweights.com/news/nemotron-3-5-parse-4kv5