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.
Alternatives to MiniCPM-OCR-Jev
120 open-weight models that do the same job as MiniCPM-OCR-Jev (2.2B 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.
Same architecture as LightOnOCR-2-1B, new capabilities. LightOnOCR-3-1B keeps the architecture of LightOn's previous LightOnOCR-2 models, so switching requires no change, and adds the new grounding, image description and chart extraction features.
1B16K ctx Apache 2.04.4K 33Oct 2026- Same category
- Smaller (1B vs 2.2B)
- Commercial use OK
Full BF16 version of the model. We recommend this variant for inference and further fine-tuning.
1.2B8K ctx Apache 2.014.9K 256Oct 2025- Same category
- Similar size (1.2B vs 2.2B)
- Commercial use OK
Smallest model. LightOnOCR-3-0.8B is the lightest model of LightOn's LightOnOCR-3 family, with the same layout and visual understanding features.
853M256K ctx Apache 2.014.8K 104Oct 2026- Same category
- Smaller (853M vs 2.2B)
- Commercial use OK
We are pleased to announce the release of OvisOCR2, a compact 0.8B end-to-end model for page-level document parsing. Given a document page image, OvisOCR2 generates a Markdown representation in natural reading order, covering text, formulas, tables, and visual regions.
853M256K ctx Apache 2.023.9K 504Jul 2026- Same category
- Smaller (853M vs 2.2B)
- Commercial use OK
Sarashina2.2-OCR is an end-to-end 3B-parameter OCR model developed by SB Intuitions, specifically tailored for parsing Japanese and English documents.
3.9B16K ctx MIT1.3K 34Mar 2026- Same category
- Similar size (3.9B vs 2.2B)
- Commercial use OK
Dolphin-v2 is an enhanced universal document parsing model that substantially improves upon the original Dolphin. It seamlessly handles any document type—whether digital-born or photographed—through a document-type-aware two-stage architecture with scalable anchor prompting.
3.8B125K ctx Unknown licence1.9K 115Dec 2025- Same category
- Similar size (3.8B vs 2.2B)
PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
959M128K ctx Apache 2.016.6K 668Jan 2026- Same category
- Smaller (959M vs 2.2B)
- Commercial use OK
Nanonets-OCR-s by Nanonets is a powerful, state-of-the-art image-to-markdown OCR model that goes far beyond traditional text extraction.
3.8B125K ctx Unknown licence5K 1.6KJun 2025- Same category
- Similar size (3.8B vs 2.2B)
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 2.2B)
- Commercial use OK
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
959M128K ctx Apache 2.020.9K 1.7KOct 2025- Same category
- Smaller (959M vs 2.2B)
- Commercial use OK
Base model for fine-tuning. This is the pre-RLVR checkpoint with strong OCR capabilities, ideal as a starting point for domain adaptation and custom fine-tuning.
1B16K ctx Apache 2.03.4K 14Jan 2026- Same category
- Smaller (1B vs 2.2B)
- Commercial use OK
Best model with image localization. This model predicts both text and precise bounding boxes for embedded images, refined with RLVR using IoU-based rewards for maximum localization accuracy.
1B16K ctx Apache 2.03.1K 30Jan 2026- Same category
- Smaller (1B vs 2.2B)
- Commercial use OK
We are delighted to announce that the WePOINTS family has welcomed a new member: POINTS-Reader, a vision-language model for end-to-end document conversion, as introduced in the paper POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion.
4.1B32K ctx Apache 2.01.9K 102Aug 2025- Same category
- Similar size (4.1B vs 2.2B)
- Commercial use OK
Merged bbox variant (advanced). This model combines OCR-improving RLVR signals with bounding-box-focused RLVR updates via joint merging, preserving OCR quality while providing image localization.
1B16K ctx Apache 2.01.4K 18Jan 2026- Same category
- Smaller (1B vs 2.2B)
- Commercial use OK
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
- Smaller (1B vs 2.2B)
- Commercial use OK
This Hub repository contains a HuggingFace's transformers implementation of Florence-2 model from Microsoft.
777M4K ctx MIT347.8K 1.9KJun 2024- Same category
- Smaller (777M vs 2.2B)
- Commercial use OK
Full BF16 version of olmOCR-2-7B-1025-FP8. We recommend using the FP8 version for all practical purposes except further fine tuning.
8.3B125K ctx Apache 2.082.8K 161Oct 2025- Same category
- Larger (8.3B vs 2.2B)
- Commercial use OK
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 2.2B)
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
716M32K ctx Apache 2.0123.8K 1.6KSept 2024- Same category
- Smaller (716M vs 2.2B)
- 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
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
This Hub repository contains a HuggingFace's transformers implementation of Florence-2 model from Microsoft.
770M1K ctx MIT28K 400Jun 2024- Same category
- Smaller (770M vs 2.2B)
- Commercial use OK
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model - HF Transformers 🤗 implementation
561MApache 2.0136.6K 244Nov 2024- Same category
- Smaller (561M vs 2.2B)
- Commercial use OK