OvisOCR3 is a unified 0.8B multimodal model for OCR and document understanding. It integrates document parsing, general OCR, key information extraction, document figure captioning, and cross-page table reconstruction into a single compact model.
Alternatives to OvisOCR3
120 open-weight models that do the same job as OvisOCR3 (853M OCR), ranked by how close they are in task and size, then by popularity and how recent they are. Licence and VRAM are shown for each.
MiniCPM-OCR Jev (2B) is an OCR quality-assessment model for text, formula, and table regions. Given a region image and a candidate OCR result, it returns a score from 0 to 1 — higher means the candidate is more likely correct.
2.2B256K ctx Apache 2.079.5K 100Oct 2026- Same category
- Larger (2.2B vs 853M)
- Commercial use OK
- Newer release
Merged variant for extra robustness (advanced). This model combines the base checkpoint with RLVR-trained weights using task arithmetic merging, providing improved consistency across challenging document categories.
1B16K ctx Apache 2.0379 14Jan 2026- Same category
- Similar size (1B vs 853M)
- Commercial use OK
Please refer to the official vLLM recipe for deployment details:
3.3BA1.1B32K ctx MIT5.6M 5KJun 2026- Same category
- Larger (3.3B vs 853M)
- Commercial use OK
- Widely used
This is the model card of a 🤗 transformers model that has been pushed on the Hub. It has been automatically generated.
823M1K ctx Unknown licence3.9K 65Jun 2024- Same category
- Similar size (823M vs 853M)
Sparse Reference Sliding Window Attention (SR-SWA): Compresses text-visual attention interactions from ultra-long sequences down to a fixed-size set of working references (e.g., 512 tokens).
3.3BA1.1B128K ctx MIT621.8K 714Oct 2026- Same category
- Larger (3.3B vs 853M)
- Commercial use OK
- Newer release
Refer to 🌟GitHub for guidance on model inference acceleration and PDF processing, etc.
3.3BA1.1B8K ctx MIT1.8M 3.5KOct 2025- Same category
- Larger (3.3B vs 853M)
- Commercial use OK
- Widely used
This Hub repository contains a HuggingFace's transformers implementation of Florence-2 model from Microsoft.
232M1K ctx MIT21.3M 443Jun 2024- Same category
- Smaller (232M vs 853M)
- Commercial use OK
- Widely used
MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm Zhang Li, Yuliang Liu, Qiang Liu, Zhiyin Ma, Ziyang Zhang, Shuo Zhang, Zidun Guo, Jiarui Zhang, Xinyu Wang, Xiang Bai
1.2BUnknown licence125 33Jul 2025- Same category
- Similar size (1.2B vs 853M)
Granite Docling is a multimodal Image-Text-to-Text model engineered for efficient document conversion. It preserves the core features of Docling while maintaining seamless integration with DoclingDocuments to ensure full compatibility.
258M8K ctx Apache 2.0423.9K 1.3KMay 2025- Same category
- Smaller (258M vs 853M)
- Commercial use OK
We present dots.mocr. Beyond achieving state-of-the-art (SOTA) performance in standard multilingual document parsing among models of comparable size, dots.mocr excels at converting structured graphics (e.g., charts, UI layouts, scientific figures and etc.) directly into SVG code.
3B128K ctx MIT57.4K 200Mar 2026- Same category
- Larger (3B vs 853M)
- Commercial use OK
dots.ocr is a powerful, multilingual document parser that unifies layout detection and content recognition within a single vision-language model while maintaining good reading order. Despite its compact 1.7B-parameter LLM foundation, it achieves state-of-the-art(SOTA) performance.
3B128K ctx MIT337.2K 1.3KJul 2025- Same category
- Larger (3B vs 853M)
- Commercial use OK
Refer to 🌟GitHub for guidance on model inference acceleration and PDF processing, etc.
3.4BA1.2B8K ctx Apache 2.0183.6K 1.2KJan 2026- Same category
- Larger (3.4B vs 853M)
- Commercial use OK
Nanonets-OCR2 by Nanonets is a family of powerful, state-of-the-art image-to-markdown OCR models that go far beyond traditional text extraction.
3.8B125K ctx Unknown licence892.7K 518Oct 2025- Same category
- Larger (3.8B vs 853M)
Dolphin (Document Image Parsing via Heterogeneous Anchor Prompting) is a novel multimodal document image parsing model that follows an analyze-then-parse paradigm.
398M4K ctx MIT529 39Oct 2025- Same category
- Smaller (398M vs 853M)
- Commercial use OK
Nanonets-OCR2 by Nanonets is a family of powerful, state-of-the-art image-to-markdown OCR models that go far beyond traditional text extraction.
1.6B32K ctx Apache 2.0176 51Oct 2025- Same category
- Similar size (1.6B vs 853M)
- Commercial use OK
Falcon OCR is a 270M parameter early-fusion vision-language model for document OCR. Given an image, it can produce plain text, LaTeX for formulas, or HTML for tables.
270M16K ctx Apache 2.05.5K 179Feb 2026- Same category
- Smaller (270M vs 853M)
- Commercial use OK
Chandra 2 is a state of the art OCR model from Datalab that outputs markdown, HTML, and JSON. It is highly accurate at extracting text from images and PDFs, while preserving layout information.
5.3B256K ctx OpenRAIL1.3M 610Mar 2026- Same category
- Larger (5.3B vs 853M)
Dolphin (Document Image Parsing via Heterogeneous Anchor Prompting) is a novel multimodal document image parsing model that follows an analyze-then-parse paradigm.
398M4K ctx MIT670 521May 2025- Same category
- Smaller (398M vs 853M)
- Commercial use OK
PP-OCRv6 is a lightweight OCR system that combines architectural innovation with data-centric optimization. It redesigns the backbone, detection neck, and recognition neck around a unified MetaFormer-style building block with structural reparameterization.
?BApache 2.047.4K 36Jun 2026- Same category
- Commercial use OK
PP-OCRv5_server_det is one of the PP-OCRv5_det series, the latest generation of text detection models developed by the PaddleOCR team.
?BApache 2.0469.8K 75Jun 2025- Same category
- Commercial use OK
This model is the pretrained version of Pix2Struct, use this model for fine-tuning purposes only.
1.3BApache 2.0623 41Mar 2023- Same category
- Similar size (1.3B vs 853M)
- Commercial use OK
en_PP-OCRv5_mobile_rec is one of the PP-OCRv5_rec that are the latest generation text line recognition models developed by PaddleOCR team. It aims to efficiently and accurately support the recognition of English. The key accuracy metrics are as follow:
?BApache 2.0202.6K 3Aug 2025- Same category
- Commercial use OK
jina-ocr-v1 is an end-to-end document parsing model designed for high-quality OCR at an efficient serving point. The model builds on DeepSeek-OCR and inherits two of its efficiency-oriented components: a DeepEncoder vision tower that represents a 1024×1024 global view with 256 visual tokens and…
3.4BA1.2B32K ctx CC BY-NC 4.01.2K 207Sept 2026- Same category
- Larger (3.4B vs 853M)
Best OCR model. LightOnOCR-3-4B is the largest and most accurate model of the LightOnOCR-3 family, LightOn's new generation of lightweight end-to-end OCR models with layout and visual understanding. We recommend it for most OCR tasks.
4.5B256K ctx Apache 2.013.1K 150Oct 2026- Same category
- Larger (4.5B vs 853M)
- Commercial use OK