nvidia/Nemotron-3.5-Parse

Nemotron 3.5 Parse

Description:

Nemotron 3.5 Parse is a document image parser that produces structured, machine-readable text with semantic layout classes, bounding boxes, and reading order. It combines a C-RADIOv4-SO400M vision encoder with a 10-layer mBART decoder that consumes the visual sequence as a causal prefix. The release uses dynamic rectangular NaViT preprocessing, content-normalized coordinates, grouped-query self-attention (16 query heads and 8 key/value heads), a 72,505-token multilingual tokenizer, and chart-aware output through the `` token. It is intended for document understanding, information retrieval, data extraction, and multimodal data-curation workflows.

Nemotron 3.5 Parse was developed by NVIDIA as a part of Nemotron.

This model is ready for commercial or non-commercial use.

Benchmark highlights

Detailed benchmarks: [ParseBench](#parsebench) · [IndicVisionBench](#indicvisionbench-ocr) · [MOSCAR](#moscar-multilingual-ocr).

| Model | Mean ↑ | Tables ↑ | Charts ↑ | Content Faithfulness ↑ | Semantic Formatting ↑ | Visual Grounding ↑ | | :--- | ---: | ---: | ---: | ---: | ---: | ---: | | Nemotron 3.5 Parse | 75.20 | 84.67 | 64.40 | 87.96 | 68.28 | 70.67 |

ParseBench results use triple pass with region union on 2,078 unique pages. See [pipeline details](#parsebench), [reproduction instructions](reference/parsebench/pipeline/README.md), and [evaluation results](reference/parsebench/pipeline/validation_metrics.json).

Additional OCR highlights (scores on a 0–100 scale):

• IndicVisionBench OCR: 83.73 ANLS-char, evaluated on 876 test pages across 10 languages. [Per-language results](#indicvisionbench-ocr).
• MOSCAR: 99.51 character bag F1, evaluated on 8,111 simply rendered synthetic pages covering 163 language/script entries. [Per-script results](#moscar-multilingual-ocr) and [full per-language results](reference/multilingual/moscar_by_language.md).

MOSCAR uses simple synthetic renderings of text in each language to test basic OCR capability. These results do not guarantee accuracy on complex scanned documents, handwriting, degraded images, or other real-world variations. Character bag F1 measures character overlap without considering character order.

License/Terms of Use:

Governing Terms: Your use of this model is governed by the OpenMDW License Agreement, version 1.1. Use of the tokenizer included in this model is governed by the MIT license and tokenizer attribution. See third-party notices for separately installed dependencies.

Tokenizer source and modifications are documented in [TOKENIZER_ATTRIBUTION.md](TOKENIZER_ATTRIBUTION.md).

The portable ParseBench pipeline has its own [license](reference/parsebench/pipeline/LICENSE) and [third-party notices](reference/parsebench/pipeline/THIRD_PARTY_NOTICES.md), including the separately installed benchmark environment. See the [component inventory](reference/package/benchmark_environment_components.json) and [package build evidence](reference/package/README.md) for exact versions and digests.

Deployment Geography:

Global

Use Case:

Nemotron 3.5 Parse is designed for developers and teams building document intelligence, retrieval-augmented generation (RAG), curator, extractor, and agentic AI applications. It can convert scanned or rendered PDFs, presentation slides, forms, reports, tables, and mixed-content document pages into structured outputs for downstream indexing, retrieval, analytics, model training-data creation, and human-in-the-loop review.

Release Date:

Hugging Face 10/17/2026 via https://huggingface.co/nvidia/Nemotron-3.5-Parse

References:

• Hugging Face Transformers mBART documentation

• NVIDIA C-RADIOv4-SO400M

Model Architecture:

Architecture Type: Transformer

Network Architecture:

• Vision Encoder: NVIDIA C-RADIOv4-SO400M (vit_so400m_patch16_224) with dynamic rectangular NaViT preprocessing

• Adapter Layer: 1D convolutions and normalization layers that compress the vision latent sequence before decoding

• Decoder: 10-layer mBART causal visual-prefix decoder with 16 query heads and 8 key/value heads

• Auxiliary Prediction Head: One trained one-step multi-token-prediction (MTP) head is included in model.safetensors. Transformers uses the normal decoder for generation; the vLLM plugin enables the bundled head for one-token speculative decoding.

• Tokenizer: 72,505 entries with multilingual and task/control tokens including `, , , and `; the decoder embedding is padded to 72,512 rows. Use of the tokenizer included in this model is governed by the MIT license and tokenizer attribution.

• Number of Parameters: 630,800,496 unique trainable parameters (approximately 0.631B), including the MTP head; shared decoder embedding/output weights are counted once

Input(s):

Input Type(s): Image, Text

Input Format(s):

• Image: Red, Green, Blue (RGB)

• Text: Prompt string

Input Parameters:

• Image: Two-Dimensional (2D)

• Text: One-Dimensional (1D)

Other Properties Related to Input:

• Recommended maximum input resolution (Width, Height): 1664, 2048

• Channel Count: 3

• Prompt format: one task prompt composed from the supported control tokens. The default prompt extracts bounding boxes, semantic classes, and text in markdown format: ``.

Output(s):

Output Type(s): Text

Output Format(s): String

Output Parameters: One-Dimensional (1D)

Other Properties Related to Output: Nemotron 3.5 Parse returns a string encoding document text, semantic element classes, and content-normalized bounding boxes. Scale x coordinates by the evaluated image width and y coordinates by its height. Postprocessing utilities can convert table or chart-associated text into LaTeX, HTML, markdown, JSON, or CSV where supported.

Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA hardware and software frameworks, the model achieves faster training and inference times compared to CPU-only solutions.

Quick Start

###...