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 surya-ocr-2.5

120 open-weight models that do the same job as surya-ocr-2.5 (689M 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
datalab-to logo

surya-ocr-2.5

datalab-to·OCR

≈2.0 GB

We also ship smaller models for line-level text detection and ocr error detection. It works on a range of documents (see usage and benchmarks).

689M256K ctx OpenRAIL
144.4KOct 2026gguf
--vram
any
--gpus
--quant
  1. facebook logo

    nougat-base

    facebook·OCR

    ≈1.3 GB

    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.

    349M4K ctx CC BY-NC 4.0
    2.4KSept 2023
    • Same category
    • Similar size (349M vs 689M)
    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
    158.7KJun 2025
    • Same category
    • Commercial use OK
    vs
  3. google logo

    pix2struct-base

    google·OCR

    ≈1.1 GB

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

    282MApache 2.0
    10.7KMar 2023
    • Same category
    • Smaller (282M vs 689M)
    • Commercial use OK
    vs
  4. 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
    90.1KJun 2025
    • Same category
    • Commercial use OK
    vs
  5. 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
    51.2KJun 2025
    • Same category
    • Commercial use OK
    vs
  6. 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
    623Mar 2023
    • Same category
    • Similar size (1.3B vs 689M)
    • Commercial use OK
    vs
  7. jinaai logo

    jina-ocr-v1

    jinaai·OCR

    ≈4.5 GB

    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 4.0
    1.2KSept 2026gguf
    • Same category
    • Larger (3.4B vs 689M)
    vs
  8. lightonai logo

    LightOnOCR-3-4B

    lightonai·OCR

    ≈5.9 GB

    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 2.0
    13.1KOct 2026gguf
    • Same category
    • Larger (4.5B vs 689M)
    • Commercial use OK
    vs
  9. 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
  10. google logo≈1.1 GB

    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 2.0
    3KMar 2023
    • Same category
    • Smaller (282M vs 689M)
    • Commercial use OK
    vs
  11. 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
  12. 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
  13. 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
  14. google logo≈1.1 GB

    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 2.0
    1.8KMar 2023
    • Same category
    • Smaller (282M vs 689M)
    • Commercial use OK
    vs
  15. opendatalab logo≈6.5 GB

    - [2026/3/24] 🔥 We release MinerU-Diffusion-V1 — a diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.

    2.7B32K ctx MIT
    173Mar 2026
    • Same category
    • Larger (2.7B vs 689M)
    • Commercial use OK
    vs
  16. google logo≈1.1 GB

    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 2.0
    946Mar 2023
    • Same category
    • Smaller (282M vs 689M)
    • Commercial use OK
    vs
  17. 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
  18. 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
  19. baidu logo

    Qianfan-OCR

    baidu·OCR

    ≈6.1 GB

    Qianfan-OCR is a 4B-parameter end-to-end document intelligence model developed by the Baidu Qianfan Team. It unifies document parsing, layout analysis, and document understanding within a single vision-language architecture.

    4.7B32K ctx Apache 2.0
    15.9KMar 2026gguf
    • Same category
    • Larger (4.7B vs 689M)
    • Commercial use OK
    vs
  20. facebook logo

    nougat-small

    facebook·OCR

    ≈1.1 GB

    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 4.0
    2.4KSept 2023
    • Same category
    • Smaller (247M vs 689M)
    • Commercial use OK
    vs
  21. sbintuitions logo

    sarashina2.2-ocr

    sbintuitions·OCR

    ≈5.1 GB

    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 MIT
    1.3KMar 2026
    • Same category
    • Larger (3.9B vs 689M)
    • Commercial use OK
    vs
  22. ByteDance logo

    Dolphin-v2

    ByteDance·OCR

    ≈5.0 GB

    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 licence
    1.9KDec 2025gguf
    • Same category
    • Larger (3.8B vs 689M)
    vs
  23. nanonets logo

    Nanonets-OCR-s

    nanonets·OCR

    ≈5.0 GB

    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 licence
    5KJun 2025gguf
    • Same category
    • Larger (3.8B vs 689M)
    vs
  24. 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
    50.1KJun 2026
    • Same category
    • Smaller (19M vs 689M)
    • Commercial use OK
    vs