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.

Compare Unlimited-OCR-2 with the top 3
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. baidu logo

    Unlimited-OCR

    baidu·OCR

    ≈4.5 GB

    Please refer to the official vLLM recipe for deployment details:

    3.3BA1.1B32K ctx MIT
    5.6MJun 2026gguf
    • Same category
    • Similar size (3.3B vs 3.3B)
    • Commercial use OK
    • Widely used
    vs
  2. deepseek-ai logo

    DeepSeek-OCR

    deepseek-ai·OCR

    ≈4.5 GB

    Refer to 🌟GitHub for guidance on model inference acceleration and PDF processing, etc.

    3.3BA1.1B8K ctx MIT
    1.8MOct 2025ollama
    • Same category
    • Similar size (3.3B vs 3.3B)
    • Commercial use OK
    • Widely used
    vs
  3. deepseek-ai logo

    DeepSeek-OCR-2

    deepseek-ai·OCR

    ≈4.5 GB

    Refer to 🌟GitHub for guidance on model inference acceleration and PDF processing, etc.

    3.4BA1.2B8K ctx Apache 2.0
    199.6KJan 2026gguf
    • Same category
    • Similar size (3.4B vs 3.3B)
    • Commercial use OK
    vs
  4. nanonets logo

    Nanonets-OCR2-3B

    nanonets·OCR

    ≈5.0 GB

    Nanonets-OCR2 by Nanonets is a family of powerful, state-of-the-art image-to-markdown OCR models that go far beyond traditional text extraction.

    3.8B125K ctx Unknown licence
    898.7KOct 2025gguf
    • Same category
    • Similar size (3.8B vs 3.3B)
    vs
  5. dots-studio logo

    dots.ocr

    dots-studio·OCR

    ≈4.1 GB

    dots.ocr is a powerful, multilingual document parser that unifies layout detection and content recognition within a single vision-language model while maintaining good reading order. Despite its compact 1.7B-parameter LLM foundation, it achieves state-of-the-art(SOTA) performance.

    3B128K ctx MIT
    354.6KJul 2025gguf
    • Same category
    • Similar size (3B vs 3.3B)
    • Commercial use OK
    vs
  6. dots-studio logo

    dots.mocr

    dots-studio·OCR

    ≈4.1 GB

    We present dots.mocr. Beyond achieving state-of-the-art (SOTA) performance in standard multilingual document parsing among models of comparable size, dots.mocr excels at converting structured graphics (e.g., charts, UI layouts, scientific figures and etc.) directly into SVG code.

    3B128K ctx MIT
    58.8KMar 2026gguf
    • Same category
    • Similar size (3B vs 3.3B)
    • Commercial use OK
    vs
  7. datalab-to logo

    chandra-ocr-2

    datalab-to·OCR

    ≈6.8 GB

    Chandra 2 is a state of the art OCR model from Datalab that outputs markdown, HTML, and JSON. It is highly accurate at extracting text from images and PDFs, while preserving layout information.

    5.3B256K ctx OpenRAIL
    1.3MMar 2026gguf
    • Same category
    • Similar size (5.3B vs 3.3B)
    vs
  8. 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
    75.8KOct 2026gguf
    • Same category
    • Similar size (2.2B vs 3.3B)
    • Commercial use OK
    vs
  9. 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
    • Similar size (3.4B vs 3.3B)
    vs
  10. 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
    13.3KOct 2026gguf
    • Same category
    • Similar size (4.5B vs 3.3B)
    • Commercial use OK
    vs
  11. 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
    15.8KMar 2026gguf
    • Same category
    • Similar size (4.7B vs 3.3B)
    • Commercial use OK
    vs
  12. 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
    • Similar size (3.9B vs 3.3B)
    • Commercial use OK
    vs
  13. 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
    • Similar size (3.8B vs 3.3B)
    vs
  14. 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
    • Smaller (1.3B vs 3.3B)
    • Commercial use OK
    • Widely used
    vs
  15. 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
    261.9KOct 2026gguf
    • Same category
    • Smaller (1.3B vs 3.3B)
    • Commercial use OK
    vs
  16. 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
    5.3KJun 2025gguf
    • Same category
    • Similar size (3.8B vs 3.3B)
    vs
  17. tencent logo

    POINTS-Reader

    tencent·OCR

    ≈5.4 GB

    We are delighted to announce that the WePOINTS family has welcomed a new member: POINTS-Reader, a vision-language model for end-to-end document conversion, as introduced in the paper POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion.

    4.1B32K ctx Apache 2.0
    1.8KAug 2025
    • Same category
    • Similar size (4.1B vs 3.3B)
    • Commercial use OK
    vs
  18. 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
    178Mar 2026
    • Same category
    • Similar size (2.7B vs 3.3B)
    • 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
    18.2KAug 2026gguf
    • Same category
    • Smaller (1.4B vs 3.3B)
    • Commercial use OK
    vs
  20. 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
    614.4KNov 2025gguf
    • Same category
    • Smaller (1.1B vs 3.3B)
    vs
  21. 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
    406.6KOct 2026gguf
    • Same category
    • Smaller (853M vs 3.3B)
    • Commercial use OK
    vs
  22. 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
    699.7KJan 2026gguf
    • Same category
    • Smaller (1B vs 3.3B)
    • Commercial use OK
    vs
  23. allenai logo

    olmOCR-2-7B-1025

    allenai·OCR

    ≈10 GB

    Full BF16 version of olmOCR-2-7B-1025-FP8. We recommend using the FP8 version for all practical purposes except further fine tuning.

    8.3B125K ctx Apache 2.0
    82.6KOct 2025gguf
    • Same category
    • Larger (8.3B vs 3.3B)
    • Commercial use OK
    vs
  24. 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
    34.9KMay 2026gguf
    • Same category
    • Smaller (1.2B vs 3.3B)
    • Commercial use OK
    vs