NVIDIA-Nemotron-Parse

NVIDIA Nemotron Parse v1.1 is designed to understand document semantics and extract text and tables elements with spatial grounding. Given an image, NVIDIA Nemotron Parse v1.1 produces structured annotations, including formatted text, bounding-boxes and the corresponding semantic classes, ordered according to the document's reading flow. It overcomes the shortcomings of traditional OCR technologies that struggle with complex document layouts with structural variability, and helps transform unstructured documents into actionable and machine-usable representations. This has several downstream benefits such as increasing the availability of training-data for Large Language Models (LLMs), improving the accuracy of extractor, curator, retriever and AI agentic applications, and enhancing document understanding pipelines.

This model is ready for commercial use.

[Note]: we recently released an updated Nemotron-Parse-v1.2

License

GOVERNING TERMS: The NIM container is governed by the NVIDIA Software License Agreement and Product-Specific Terms for NVIDIA AI Products. Use of this model is governed by the NVIDIA Open Model License Agreement. Use of the tokenizer included in this model is governed by the CC-BY-4.0 license.

Deployment Geography:

Global

Use Case:

NVIDIA Nemotron Parse v1.1 will be capable of comprehensive text understanding and document structure understanding. It will be used in retriever and curator solutions. Its text extraction datasets and capabilities will help with LLM and VLM training, as well as improve run-time inference accuracy of VLMs. The NVIDIA Nemotron Parse v1.1 model will perform text extraction from PDF and PPT documents. The NVIDIA Nemotron Parse v1.1 can classify the objects (title, section, caption, index, footnote, lists, tables, bibliography, image) in a given document, and provide bounding boxes with coordinates.

Release Date:

November 17, 2025

References

• https://huggingface.co/docs/transformers/en/model_doc/mbart

Model Architecture

Architecture Type :

Transformer-based vision-encoder-decoder model

Network Architecture

• Vision Encoder: ViT-H model (https://huggingface.co/nvidia/C-RADIO)
• Adapter Layer: 1D convolutions & norms to compress dimensionality and sequence length of the latent space (13184 tokens to 3201 tokens)
• Decoder: mBart [1] 10 blocks
• Tokenizer: Use of the tokenizer included in this model is governed by the CC-BY-4.0 license
• Number of Parameters:

Computational Load (For NVIDIA Models Only)

Cumulative Compute: 2.2e+22 Estimated Energy and Emissions for Model Training: Energy Consumption: 7,827.46 kWh Carbon Emissions: 3.21 tCO2e

Input

• Input Type: Image, Text
• Input Type(s): Red, Green, Blue (RGB) + Prompt (String)
• Input Parameters: 2D, 1D

• Other Properties Related to Input:
  • Max Input Resolution (Width, Height): 1648, 2048
  • Min Input Resolution (Width, Height): 1024, 1280
• Channel Count: 3

Output

• Output Type: Text
• Output Format: String
• Output Parameters: 1D

• Other Properties Related to Output:
  • NVIDIA Nemotron Parse v1.1 output format is a string which encodes text content (formatted or not) as well as bounding boxes and class attributes. In the default prompt setting, text content is represented as markdown, and math expressions as LaTeX, enclosed in [..] or (..). If a mathematical expression does not require LaTeX formatting to be represented (e.g., consisting only of characters and subscripts/superscripts), it is represented as markdown. Tables are represented as LaTeX. Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.

Software Integration:

Runtime Engine(s): TensorRT-LLM

Supported Hardware Microarchitecture Compatibility: NVIDIA Hopper/NVIDIA Ampere/NVIDIA Turing

Supported Operating System(s): Linux

The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.

Model Version:

V1.1. A faster version of Nemotron-Parse is available as well: Nemotron-Parse-v1.1-TC

Quick Start

Install dependencies in your environment

pip install -r requirements.txt

Alternatively, you can use a public image nvcr.io/nvidia/pytorch:25.03-py3 with the following library versions installed on top:

pip install accelerate==1.12.0
pip install albumentations==2.0.8
pip install transformers==4.51.3
pip install timm==1.0.22

transformers==4.51.3 remains the pinned reference environment for this model. The included remote code has also been tested against newer Transformers APIs, including Transformers 5.6.2, while preserving golden output compatibility with the pinned environment.

Usage example

import torch
from PIL import Image, ImageDraw
from transformers import AutoModel, AutoProcessor, AutoTokenizer, AutoConfig, AutoImageProcessor, GenerationConfig
from postprocessing import extract_classes_bboxes, transform_bbox_to_original, postprocess_te