selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

Alternatives to Unlimited-OCR-2

120 open-weight models that do the same job as Unlimited-OCR-2 (3.3B 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.

the original
baidu logo

Unlimited-OCR-2

baidu·OCR

≈4.5 GB

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 MIT
612.1KOct 2026gguf
--vram
any
--gpus
--quant
  1. PaddlePaddle logo

    PP-OCRv6_small_det

    PaddlePaddle·OCR

    ? GB

    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 2.0
    12.9KJun 2026
    • Same category
    • Commercial use OK
    vs
  2. PaddlePaddle logo

    PP-OCRv5_server_rec

    PaddlePaddle·OCR

    ? GB

    PP-OCRv5_server_rec is one of the PP-OCRv5_rec that are the latest generation text line recognition models developed by PaddleOCR team.

    ?BApache 2.0
    159.1KJun 2025
    • Same category
    • Commercial use OK
    vs
  3. lightonai logo≈2.8 GB

    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 2.0
    392Jan 2026gguf
    • Same category
    • Smaller (1B vs 3.3B)
    • Commercial use OK
    vs
  4. microsoft logo

    Florence-2-large

    microsoft·OCR

    ≈2.2 GB

    This Hub repository contains a HuggingFace's transformers implementation of Florence-2 model from Microsoft.

    777M4K ctx MIT
    353.9KJun 2024
    • Same category
    • Smaller (777M vs 3.3B)
    • Commercial use OK
    vs
  5. PaddlePaddle logo

    PP-OCRv5_mobile_det

    PaddlePaddle·OCR

    ? GB

    PP-OCRv5_mobile_det is one of the PP-OCRv5_det series, the latest generation of text detection models developed by the PaddleOCR team.

    ?BApache 2.0
    91.2KJun 2025
    • Same category
    • Commercial use OK
    vs
  6. PaddlePaddle logo

    PP-OCRv5_mobile_rec

    PaddlePaddle·OCR

    ? GB

    PP-OCRv5_mobile_rec is one of the PP-OCRv5_rec that are the latest generation text line recognition models developed by PaddleOCR team.

    ?BApache 2.0
    52.2KJun 2025
    • Same category
    • Commercial use OK
    vs
  7. bodhan-ai logo

    indic-ocr

    bodhan-ai·OCR

    ? GB

    Document parsing for English and 22 Indian languages, printed and handwritten. A page image in; reading-ordered Markdown out, with math as LaTeX and tables as HTML or Markdown, plus per-block JSON.

    ?BCustom licence
    1.3KAug 2026gguf
    • Same category
    vs
  8. stepfun-ai logo

    GOT-OCR2_0

    stepfun-ai·OCR

    ≈2.1 GB

    General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

    716M32K ctx Apache 2.0
    124.7KSept 2024gguf
    • Same category
    • Smaller (716M vs 3.3B)
    • Commercial use OK
    vs
  9. PaddlePaddle logo

    PP-OCRv6_tiny_rec

    PaddlePaddle·OCR

    ? GB

    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 2.0
    1.6KJun 2026
    • Same category
    • Commercial use OK
    vs
  10. echo840 logo

    MonkeyOCR-pro-1.2B

    echo840·OCR

    ≈3.2 GB

    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 licence
    94Jul 2025
    • Same category
    • Smaller (1.2B vs 3.3B)
    vs
  11. PaddlePaddle logo

    PP-OCRv6_tiny_det

    PaddlePaddle·OCR

    ? GB

    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 2.0
    1.4KJun 2026
    • Same category
    • Commercial use OK
    vs
  12. nvidia logo

    nemotron-ocr-v2

    nvidia·OCR

    ? GB

    Nemotron OCR v2 is a state-of-the-art multilingual text recognition model designed for robust end-to-end optical character recognition (OCR) on complex real-world images.

    ?BNVIDIA Open Model License
    2KApr 2026
    • Same category
    • Commercial use OK
    vs
  13. PaddlePaddle logo? GB

    korean_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 Korean. The key accuracy metrics are as follow:

    ?BApache 2.0
    7.5KJul 2025
    • Same category
    • Commercial use OK
    vs
  14. PaddlePaddle logo

    PP-DocLayout_plus-L

    PaddlePaddle·OCR

    ? GB

    A higher-precision layout area localization model trained on a self-built dataset containing Chinese and English papers, PPT, multi-layout magazines, contracts, books, exams, ancient books and research reports using RT-DETR-L.

    ?BApache 2.0
    9KJun 2025
    • Same category
    • Commercial use OK
    vs
  15. microsoft logo

    Florence-2-large-ft

    microsoft·OCR

    ≈2.2 GB

    This Hub repository contains a HuggingFace's transformers implementation of Florence-2 model from Microsoft.

    770M1K ctx MIT
    28.2KJun 2024
    • Same category
    • Smaller (770M vs 3.3B)
    • Commercial use OK
    vs
  16. stepfun-ai logo

    GOT-OCR-2.0-hf

    stepfun-ai·OCR

    ≈1.8 GB

    General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model - HF Transformers 🤗 implementation

    561MApache 2.0
    136.2KNov 2024
    • Same category
    • Smaller (561M vs 3.3B)
    • Commercial use OK
    vs
  17. google logo

    pix2struct-large

    google·OCR

    ≈3.5 GB

    This model is the pretrained version of Pix2Struct, use this model for fine-tuning purposes only.

    1.3BApache 2.0
    616Mar 2023
    • Same category
    • Smaller (1.3B vs 3.3B)
    • Commercial use OK
    vs
  18. microsoft logo

    Florence-2-base

    microsoft·OCR

    ≈1.0 GB

    This Hub repository contains a HuggingFace's transformers implementation of Florence-2 model from Microsoft.

    232M1K ctx MIT
    20.5MJun 2024
    • Same category
    • Smaller (232M vs 3.3B)
    • Commercial use OK
    • Widely used
    vs
  19. HuggingFaceM4 logo

    Florence-2-DocVQA

    HuggingFaceM4·OCR

    ≈2.3 GB

    This is the model card of a 🤗 transformers model that has been pushed on the Hub. It has been automatically generated.

    823M1K ctx Unknown licence
    3.8KJun 2024
    • Same category
    • Smaller (823M vs 3.3B)
    vs
  20. PaddlePaddle logo

    PP-OCRv6_medium_rec

    PaddlePaddle·OCR

    ≈0.5 GB

    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 2.0
    51.4KJun 2026
    • Same category
    • Smaller (19M vs 3.3B)
    • Commercial use OK
    vs
  21. nvidia logo

    nemotron-ocr-v1

    nvidia·OCR

    ? GB

    The Nemotron OCR v1 model is a state-of-the-art text recognition model designed for robust end-to-end optical character recognition (OCR) on complex real-world images.

    ?BNVIDIA Open Model License
    233Oct 2025
    • Same category
    • Commercial use OK
    vs
  22. ibm-granite logo

    granite-docling-258M

    ibm-granite·OCR

    ≈1.1 GB

    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 2.0
    421.3KMay 2025gguf
    • Same category
    • Smaller (258M vs 3.3B)
    • Commercial use OK
    vs
  23. datalab-to logo

    indra-ocr

    datalab-to·OCR

    ≈0.5 GB

    Indra OCR is a 1M-parameter OCR model that reads up to 49 pages per second on CPU. It turns PDFs and images into markdown, plain text, or JSON with boxes, and it has these features:

    1MOpenRAIL
    6.2KOct 2026
    • Same category
    • Smaller (1M vs 3.3B)
    vs
  24. PaddlePaddle logo

    PP-OCRv6_small_rec

    PaddlePaddle·OCR

    ≈0.5 GB

    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 2.0
    12.4KJun 2026
    • Same category
    • Smaller (5M vs 3.3B)
    • Commercial use OK
    vs