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.

Compare surya-ocr-2.5 with the top 3
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
129.8KOct 2026gguf
--vram
any
--gpus
--quant
  1. datalab-to logo

    surya-ocr-2

    datalab-to·OCR

    ≈2.0 GB

    It works on a range of documents (see usage and benchmarks).

    686M256K ctx OpenRAIL
    668.5KMay 2026gguf
    • Same category
    • Similar size (686M vs 689M)
    vs
  2. ATH-MaaS logo

    OvisOCR3

    ATH-MaaS·OCR

    ≈2.4 GB

    OvisOCR3 is a unified 0.8B multimodal model for OCR and document understanding. It integrates document parsing, general OCR, key information extraction, document figure captioning, and cross-page table reconstruction into a single compact model.

    853M256K ctx Apache 2.0
    375.6KOct 2026gguf
    • Same category
    • Similar size (853M vs 689M)
    • Commercial use OK
    vs
  3. lightonai logo

    LightOnOCR-2-1B

    lightonai·OCR

    ≈2.8 GB

    Best OCR model . LightOnOCR-2-1B is LightOn's flagship OCR model, refined with RLVR training for maximum accuracy. We recommend this variant for most OCR tasks.

    1B16K ctx Apache 2.0
    726.3KJan 2026gguf
    • Same category
    • Similar size (1B vs 689M)
    • Commercial use OK
    vs
  4. lightonai logo

    LightOnOCR-3-0.8B

    lightonai·OCR

    ≈2.4 GB

    Smallest model. LightOnOCR-3-0.8B is the lightest model of LightOn's LightOnOCR-3 family, with the same layout and visual understanding features.

    853M256K ctx Apache 2.0
    15.1KOct 2026gguf
    • Same category
    • Similar size (853M vs 689M)
    • Commercial use OK
    vs
  5. ATH-MaaS logo

    OvisOCR2

    ATH-MaaS·OCR

    ≈2.4 GB

    We are pleased to announce the release of OvisOCR2, a compact 0.8B end-to-end model for page-level document parsing. Given a document page image, OvisOCR2 generates a Markdown representation in natural reading order, covering text, formulas, tables, and visual regions.

    853M256K ctx Apache 2.0
    25KJul 2026gguf
    • Same category
    • Similar size (853M vs 689M)
    • Commercial use OK
    vs
  6. PaddlePaddle logo

    PaddleOCR-VL-1.6

    PaddlePaddle·OCR

    ≈2.6 GB

    PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training

    959M128K ctx Apache 2.0
    99.7KMay 2026gguf
    • Same category
    • Similar size (959M vs 689M)
    • Commercial use OK
    vs
  7. openbmb logo

    MiniCPM-OCR-1.0

    openbmb·OCR

    ≈3.4 GB

    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.

    1.3B256K ctx Apache 2.0
    243.4KOct 2026gguf
    • Same category
    • Similar size (1.3B vs 689M)
    • Commercial use OK
    vs
  8. zai-org logo

    GLM-OCR

    zai-org·OCR

    ≈3.5 GB

    GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture. It introduces Multi-Token Prediction (MTP) loss and stable full-task reinforcement learning to improve training efficiency, recognition accuracy, and generalization.

    1.3B128K ctx MIT
    1.9MJan 2026ollama
    • Same category
    • Similar size (1.3B vs 689M)
    • Commercial use OK
    • Widely used
    vs
  9. tencent logo

    HunyuanOCR

    tencent·OCR

    ≈3.0 GB

    📦 Model layout. This repository hosts HunyuanOCR-1.5 checkpoint at the root (target base weights). The DFlash speculative-decoding draft lives under dflash/, and the previous HunyuanOCR-1.0 is archived under v1.0/ (load it with subfolder="v1.0", or download the v1.0/ directory directly).

    1.1B128K ctx Tencent Hunyuan Community License
    617.7KNov 2025gguf
    • Same category
    • Similar size (1.1B vs 689M)
    vs
  10. 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
    125.1KSept 2024gguf
    • Same category
    • Similar size (716M vs 689M)
    • Commercial use OK
    vs
  11. 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
    368.6KJun 2024
    • Same category
    • Similar size (777M vs 689M)
    • Commercial use OK
    vs
  12. PaddlePaddle logo

    PaddleOCR-VL-1.5

    PaddlePaddle·OCR

    ≈2.6 GB

    PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing

    959M128K ctx Apache 2.0
    21.9KJan 2026gguf
    • Same category
    • Similar size (959M vs 689M)
    • Commercial use OK
    vs
  13. lightonai logo

    LightOnOCR-3-1B

    lightonai·OCR

    ≈2.8 GB

    Same architecture as LightOnOCR-2-1B, new capabilities. LightOnOCR-3-1B keeps the architecture of LightOn's previous LightOnOCR-2 models, so switching requires no change, and adds the new grounding, image description and chart extraction features.

    1B16K ctx Apache 2.0
    4.4KOct 2026gguf
    • Same category
    • Similar size (1B vs 689M)
    • Commercial use OK
    vs
  14. opendatalab logo

    MinerU2.5-Pro-2605-1.2B

    opendatalab·OCR

    ≈3.1 GB

    MinerU2.5-Pro is our latest document parsing model (PDF-to-Markdown) that establishes a new industry standard. By focusing entirely on data engineering without altering the original 1.2B-parameter architecture, it delivers exceptional results across the board:

    1.2B8K ctx Apache 2.0
    35.2KMay 2026gguf
    • Same category
    • Similar size (1.2B vs 689M)
    • Commercial use OK
    vs
  15. 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
    129.8KNov 2024
    • Same category
    • Similar size (561M vs 689M)
    • Commercial use OK
    vs
  16. opendatalab logo

    MinerU2.5-Pro-2604-1.2B

    opendatalab·OCR

    ≈3.1 GB

    MinerU2.5-Pro is our latest document parsing model (PDF-to-Markdown) that establishes a new industry standard. By focusing entirely on data engineering without altering the original 1.2B-parameter architecture, it delivers exceptional results across the board:

    1.2B8K ctx Apache 2.0
    27.9KApr 2026gguf
    • Same category
    • Similar size (1.2B vs 689M)
    • Commercial use OK
    vs
  17. PaddlePaddle logo

    PaddleOCR-VL

    PaddlePaddle·OCR

    ≈2.6 GB

    PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model

    959M128K ctx Apache 2.0
    17.2KOct 2025gguf
    • Same category
    • Similar size (959M vs 689M)
    • Commercial use OK
    vs
  18. opendatalab logo

    MinerU2.5-2509-1.2B

    opendatalab·OCR

    ≈3.1 GB

    MinerU2.5 is a 1.2B-parameter vision-language model for document parsing that achieves state-of-the-art accuracy with high computational efficiency.

    1.2B16K ctx AGPL 3.0
    77.6KSept 2025gguf
    • Same category
    • Similar size (1.2B vs 689M)
    • Commercial use OK
    vs
  19. XingChen-AGI logo

    TeleOCR

    XingChen-AGI·OCR

    ≈3.7 GB

    TeleOCR is a lightweight (~1.2B parameters), open-source Vision-Language Model designed specifically for document parsing.

    1.4B125K ctx Apache 2.0
    18.7KAug 2026gguf
    • Same category
    • Larger (1.4B vs 689M)
    • Commercial use OK
    vs
  20. 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
    28.5KJun 2024
    • Same category
    • Similar size (770M vs 689M)
    • Commercial use OK
    vs
  21. lightonai logo

    LightOnOCR-2-1B-base

    lightonai·OCR

    ≈2.8 GB

    Base model for fine-tuning. This is the pre-RLVR checkpoint with strong OCR capabilities, ideal as a starting point for domain adaptation and custom fine-tuning.

    1B16K ctx Apache 2.0
    3.6KJan 2026gguf
    • Same category
    • Similar size (1B vs 689M)
    • Commercial use OK
    vs
  22. lightonai logo

    LightOnOCR-2-1B-bbox

    lightonai·OCR

    ≈2.8 GB

    Best model with image localization. This model predicts both text and precise bounding boxes for embedded images, refined with RLVR using IoU-based rewards for maximum localization accuracy.

    1B16K ctx Apache 2.0
    2.9KJan 2026gguf
    • Same category
    • Similar size (1B vs 689M)
    • Commercial use OK
    vs
  23. lightonai logo

    LightOnOCR-1B-1025

    lightonai·OCR

    ≈3.1 GB

    Full BF16 version of the model. We recommend this variant for inference and further fine-tuning.

    1.2B8K ctx Apache 2.0
    14KOct 2025gguf
    • Same category
    • Similar size (1.2B vs 689M)
    • Commercial use OK
    vs
  24. lightonai logo≈2.8 GB

    Merged bbox variant (advanced). This model combines OCR-improving RLVR signals with bounding-box-focused RLVR updates via joint merging, preserving OCR quality while providing image localization.

    1B16K ctx Apache 2.0
    1.5KJan 2026gguf
    • Same category
    • Similar size (1B vs 689M)
    • Commercial use OK
    vs