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. echo840 logo

    MonkeyOCR

    echo840·OCR

    ? 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

    ?BUnknown licence
    118Jun 2025
    • Same category
    vs
  2. tiiuae logo

    Falcon-OCR

    tiiuae·OCR

    ≈1.1 GB

    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 2.0
    5.6KFeb 2026
    • Same category
    • Smaller (270M vs 3.3B)
    • Commercial use OK
    vs
  3. PaddlePaddle logo≈0.6 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.

    22MApache 2.0
    2.2KJun 2026
    • Same category
    • Smaller (22M vs 3.3B)
    • Commercial use OK
    vs
  4. PaddlePaddle logo≈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
    1.8KJun 2026
    • Same category
    • Smaller (19M vs 3.3B)
    • Commercial use OK
    vs
  5. PaddlePaddle logo≈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.

    438KApache 2.0
    1.2KJun 2026
    • Same category
    • Smaller (438K vs 3.3B)
    • Commercial use OK
    vs
  6. PaddlePaddle logo≈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.

    2MApache 2.0
    716Jun 2026
    • Same category
    • Smaller (2M vs 3.3B)
    • Commercial use OK
    vs
  7. microsoft logo

    Florence-2-base-ft

    microsoft·OCR

    ≈1.0 GB

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

    232M1K ctx MIT
    155.6KJun 2024
    • Same category
    • Smaller (232M vs 3.3B)
    • Commercial use OK
    vs
  8. ByteDance logo

    Dolphin-1.5

    ByteDance·OCR

    ≈1.4 GB

    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 MIT
    522Oct 2025
    • Same category
    • Smaller (398M vs 3.3B)
    • Commercial use OK
    vs
  9. 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-agreement
    171Jul 2026gguf
    • Same category
    • Larger (33B vs 3.3B)
    • Commercial use OK
    vs
  10. ByteDance logo

    Dolphin

    ByteDance·OCR

    ≈1.4 GB

    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 MIT
    668May 2025
    • Same category
    • Smaller (398M vs 3.3B)
    • Commercial use OK
    vs
  11. 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 2.0
    212Mar 2023
    • Same category
    • Commercial use OK
    vs
  12. 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 2.0
    179Mar 2023
    • Same category
    • Commercial use OK
    vs
  13. 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 2.0
    179Mar 2023
    • Same category
    • Commercial use OK
    vs
  14. vikp logo

    texify

    vikp·OCR

    ≈1.2 GB

    texify is an open-weight ocr model with 312.5M parameters from vikp, published on Hugging Face.

    312M2K ctx CC BY-SA 4.0
    47.4KDec 2023
    • Same category
    • Smaller (312M vs 3.3B)
    • Commercial use OK
    vs
  15. 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
    10.8KMar 2023
    • Same category
    • Smaller (282M vs 3.3B)
    • Commercial use OK
    vs
  16. 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
    2.3KSept 2023
    • Same category
    • Smaller (349M vs 3.3B)
    vs
  17. 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 3.3B)
    • Commercial use OK
    vs
  18. 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 3.3B)
    • Commercial use OK
    vs
  19. 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
    1.9KMar 2023
    • Same category
    • Smaller (282M vs 3.3B)
    • Commercial use OK
    vs
  20. 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
    951Mar 2023
    • Same category
    • Smaller (282M vs 3.3B)
    • Commercial use OK
    vs
  21. Qwen logo

    Qwen3.5-4B

    Qwen·Vision

    ≈4.3 GB

    Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.

    4.7B256K ctx Apache 2.0
    4.4MFeb 2026ollama
    • Related category
    • Similar size (4.7B vs 3.3B)
    • Commercial use OK
    • Widely used
    vs
  22. Qwen logo

    Qwen3.5-2B

    Qwen·Vision

    ≈2.2 GB

    Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.

    2.3B256K ctx Apache 2.0
    5.5MFeb 2026ollama
    • Related category
    • Similar size (2.3B vs 3.3B)
    • Commercial use OK
    • Widely used
    vs
  23. LiquidAI logo

    LFM2.5-VL-3B

    LiquidAI·Vision

    ≈2.8 GB

    LFM2.5-VL-3B is a multimodal variant of LFM2.5, a family of hybrid models designed for on-device deployment. It builds on LFM2-VL-3B with further mid- and post-training.

    3.1B32K ctx lfm1.0
    45.2KAug 2026gguf
    • Related category
    • Similar size (3.1B vs 3.3B)
    vs
  24. Qwen logo≈4.3 GB

    Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.

    4.4B256K ctx Apache 2.0
    2.9MOct 2025ollama
    • Related category
    • Similar size (4.4B vs 3.3B)
    • Commercial use OK
    • Widely used
    vs