MiniCPM-OCR 1.0 (1.3B) is the first OCR-specific model in the MiniCPM-V/o family. It focuses on text-centric document understanding — text, tables, formulas, charts, seals, and structured information extraction — and balances quality against speed on real-world captures.
Alternatives to MiniCPM-OCR-1.0
120 open-weight models that do the same job as MiniCPM-OCR-1.0 (1.3B 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.
Chandra is an OCR model that outputs markdown, HTML, and JSON. It is highly accurate at extracting text from images and PDFs, while preserving layout information.
8.8B256K ctx OpenRAIL1.8K 533Oct 2025- Same category
- Larger (8.8B vs 1.3B)
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.
5MApache 2.012.3K 17Jun 2026- Same category
- Smaller (5M vs 1.3B)
- Commercial use OK
This model is the pretrained version of Pix2Struct, use this model for fine-tuning purposes only.
282MApache 2.010.7K 91Mar 2023- Same category
- Smaller (282M vs 1.3B)
- Commercial use OK
ArmorOCR is a two-stage framework for grounded adversarial OCR perception built on Qwen3-VL-8B-Instruct. It enables single-pass inference on the original image, without any inference-time visual transformations or tool assistance.
8.8B256K ctx Apache 2.0149 12Aug 2026- Same category
- Larger (8.8B vs 1.3B)
- Commercial use OK
This is a release of the olmOCR model that's fine tuned from Qwen2.5-VL-7B-Instruct using the olmOCR-mix-0225 dataset.
8.3B125K ctx Apache 2.0771 65Jul 2025- Same category
- Larger (8.3B vs 1.3B)
- Commercial use OK
This is a release of the olmOCR model that's fine tuned from Qwen2.5-VL-7B-Instruct using the olmOCR-mix-0225 dataset.
8.3B125K ctx Apache 2.0669 58Aug 2025- Same category
- Larger (8.3B vs 1.3B)
- 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
?BUnknown licence116 515Jun 2025- Same category
Earlier this year, the Allen Institute for AI released olmOCR, an open-source tool that performs document OCR using the Qwen2-VL-7B vision language model (VLM).
8.3B125K ctx Apache 2.01.4K 589Apr 2025- Same category
- Larger (8.3B vs 1.3B)
- Commercial use OK
Pix2Struct is an image encoder - text decoder model that is trained on image-text pairs for various tasks, including image captionning and visual question answering. The full list of available models can be found on the Table 1 of the paper:
282MApache 2.03K 36Mar 2023- Same category
- Smaller (282M vs 1.3B)
- 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.
22MApache 2.02.2K 143Jun 2026- Same category
- Smaller (22M vs 1.3B)
- 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.
19MApache 2.01.9K 28Jun 2026- Same category
- Smaller (19M vs 1.3B)
- Commercial use OK
Pix2Struct is an image encoder - text decoder model that is trained on image-text pairs for various tasks, including image captionning and visual question answering. The full list of available models can be found on the Table 1 of the paper:
282MApache 2.01.8K 50Mar 2023- Same category
- Smaller (282M vs 1.3B)
- 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.
438KApache 2.01.2K 28Jun 2026- Same category
- Smaller (438K vs 1.3B)
- Commercial use OK
Pix2Struct is an image encoder - text decoder model that is trained on image-text pairs for various tasks, including image captionning and visual question answering. The full list of available models can be found on the Table 1 of the paper:
282MApache 2.0946 47Mar 2023- Same category
- Smaller (282M vs 1.3B)
- 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.
2MApache 2.0723 29Jun 2026- Same category
- Smaller (2M vs 1.3B)
- Commercial use OK
Nougat model trained on PDF-to-markdown. It was introduced in the paper Nougat: Neural Optical Understanding for Academic Documents by Blecher et al. and first released in this repository.
247M4K ctx CC BY 4.02.4K 35Sept 2023- Same category
- Smaller (247M vs 1.3B)
- Commercial use OK
Stockmark-Nemotron-3-Nano-Omni-JapanDocReader is a Japanese document-reading multimodal model built on top of NVIDIA's Nemotron-3-Nano-Omni-30B-A3B-Reasoning. This model injects Japanese structured document parsing capability while preserving as much of the original VQA ability as possible.
33B256K ctx nvidia-open-model-agreement164 8Jul 2026- Same category
- Larger (33B vs 1.3B)
- Commercial use OK
Pix2Struct is an image encoder - text decoder model that is trained on image-text pairs for various tasks, including image captionning and visual question answering. The full list of available models can be found on the Table 1 of the paper:
?BApache 2.0217 39Mar 2023- Same category
- Commercial use OK
Pix2Struct is an image encoder - text decoder model that is trained on image-text pairs for various tasks, including image captionning and visual question answering. The full list of available models can be found on the Table 1 of the paper:
?BApache 2.0179 34Mar 2023- Same category
- Commercial use OK
Pix2Struct is an image encoder - text decoder model that is trained on image-text pairs for various tasks, including image captionning and visual question answering. The full list of available models can be found on the Table 1 of the paper:
?BApache 2.0172 25Mar 2023- Same category
- Commercial use OK
MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 1B variant. It builds on the family's single-image, multi-image, and video understanding capabilities, combining stronger foundation capabilities with efficient visual encoding and on-device inference.
1.6B256K ctx Apache 2.0468.8K 418Oct 2026- Related category
- Similar size (1.6B vs 1.3B)
- Commercial use OK
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
1.3B256K ctx Apache 2.0194.5K 1.3KApr 2026- Related category
- Similar size (1.3B vs 1.3B)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
873M256K ctx Apache 2.02.5M 856Feb 2026- Related category
- Similar size (873M vs 1.3B)
- Commercial use OK
- Widely used
NVIDIA Nemotron Parse 2.0 transforms document images into structured, machine-readable representations with text, layout classes, bounding boxes, and reading-order information.
903M9K ctx Custom licence650.6K 136Jun 2026- Related category
- Similar size (903M vs 1.3B)
- Commercial use OK