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 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.

the original
openbmb logo

MiniCPM-OCR-Jev

openbmb·OCR

≈5.5 GB

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.

2.2B256K ctx Apache 2.0
79.5KOct 2026gguf
--vram
any
--gpus
--quant
  1. 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
    5.5KFeb 2026
    • Same category
    • Smaller (270M vs 2.2B)
    • Commercial use OK
    vs
  2. 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
    12.3KJun 2026
    • Same category
    • Smaller (5M vs 2.2B)
    • Commercial use OK
    vs
  3. 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
    670May 2025
    • Same category
    • Smaller (398M vs 2.2B)
    • Commercial use OK
    vs
  4. 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
    116Jun 2025
    • Same category
    vs
  5. 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 2.2B)
    • 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.

    19MApache 2.0
    1.9KJun 2026
    • Same category
    • Smaller (19M vs 2.2B)
    • Commercial use OK
    vs
  7. 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 2.2B)
    • Commercial use OK
    vs
  8. 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
    48.2KDec 2023
    • Same category
    • Smaller (312M vs 2.2B)
    • Commercial use OK
    vs
  9. 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
    156.3KJun 2024
    • Same category
    • Smaller (232M vs 2.2B)
    • Commercial use OK
    vs
  10. 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
    723Jun 2026
    • Same category
    • Smaller (2M vs 2.2B)
    • Commercial use OK
    vs
  11. 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
    164Jul 2026gguf
    • Same category
    • Larger (33B vs 2.2B)
    • Commercial use OK
    vs
  12. 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
    • Smaller (349M vs 2.2B)
    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
    217Mar 2023
    • Same category
    • Commercial use OK
    vs
  14. 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
  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
    10.7KMar 2023
    • Same category
    • Smaller (282M vs 2.2B)
    • Commercial use OK
    vs
  16. 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
    172Mar 2023
    • Same category
    • Commercial use OK
    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 2.2B)
    • Commercial use OK
    vs
  18. 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 2.2B)
    • 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
    946Mar 2023
    • Same category
    • Smaller (282M vs 2.2B)
    • 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 2.2B)
    • Commercial use OK
    vs
  21. 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
    5.4MFeb 2026ollama
    • Related category
    • Similar size (2.3B vs 2.2B)
    • Commercial use OK
    • Widely used
    vs
  22. Qwen logo≈2.6 GB

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

    2.1B256K ctx Apache 2.0
    1.2MOct 2025ollama
    • Related category
    • Similar size (2.1B vs 2.2B)
    • Commercial use OK
    vs
  23. Qwen logo

    Qwen3.5-2B-Base

    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
    321.5KFeb 2026gguf
    • Related category
    • Similar size (2.3B vs 2.2B)
    • Commercial use OK
    vs
  24. nvidia logo

    Cosmos-Reason2-2B

    nvidia·Vision

    ≈2.5 GB

    NVIDIA Cosmos Reason 2 is an open, customizable, 2B-parameter reasoning vision language model (VLM) for physical AI and robotics that enables robots and vision AI agents to reason like humans, using prior knowledge, physics understanding and common sense to understand and act in the real world.

    2.4B256K ctx NVIDIA Open Model License
    475.6KDec 2025gguf
    • Related category
    • Similar size (2.4B vs 2.2B)
    • Commercial use OK
    vs