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. LiquidAI logo

    d1-3B

    LiquidAI·Vision

    ≈2.8 GB

    d1-3B is a 3B parameter decision model built on LFM2.5-VL-3B. You give it a state (text, JSON, images, or a mix) and a set of questions. It returns calibrated, typed answers in one forward pass with zero output tokens.

    3.1B32K ctx lfm1.0
    19.7KOct 2026gguf
    • Related category
    • Similar size (3.1B vs 3.3B)
    vs
  2. meta-models logo

    Muse-Glimmer-30B-assistant

    meta-models·Vision

    ≈2.2 GB

    Muse Glimmer is a 30-billion-parameter causal language model with a dedicated perception encoder, distilled from Muse Spark and purpose-built for autonomous agentic tasks on consumer hardware.

    2.6B128K ctx Apache 2.0
    109.9KAug 2026
    • Related category
    • Similar size (2.6B vs 3.3B)
    • Commercial use OK
    vs
  3. Qwen logo≈3.0 GB

    In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models.

    3.8B125K ctx Qwen Research License
    1.9MJan 2025ollama
    • Related category
    • Similar size (3.8B vs 3.3B)
    • Widely used
    vs
  4. Qwen logo

    Qwen3.5-4B-Base

    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
    504.3KFeb 2026gguf
    • Related category
    • Similar size (4.7B vs 3.3B)
    • Commercial use OK
    vs
  5. ibm-granite logo

    granite-vision-4.1-4b

    ibm-granite·Vision

    ≈3.5 GB

    Model Summary: Granite Vision 4.1 4B is a vision-language model (VLM) that delivers frontier-level performance on structured document extraction tasks — chart extraction, table extraction, and semantic key-value pair extraction — in a compact 4B parameter footprint, providing a lightweight…

    4B128K ctx Apache 2.0
    72.1KApr 2026gguf
    • Related category
    • Similar size (4B vs 3.3B)
    • Commercial use OK
    vs
  6. 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
    481KDec 2025gguf
    • Related category
    • Similar size (2.4B vs 3.3B)
    • Commercial use OK
    vs
  7. google logo

    medgemma-1.5-4b-it

    google·Vision

    ≈4.1 GB

    * License: The use of MedGemma is governed by the Health AI Developer Foundations terms of use. MedGemma has not been evaluated or optimized for multi-turn applications.

    4.3B128K ctx health-ai-developer-foundations
    194.2KJan 2026ollama
    • Related category
    • Similar size (4.3B vs 3.3B)
    vs
  8. 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
    325.1KFeb 2026gguf
    • Related category
    • Similar size (2.3B vs 3.3B)
    • Commercial use OK
    vs
  9. nvidia logo

    LocateAnything-3B

    nvidia·Vision

    ≈3.0 GB

    LocateAnything is a vision-language model for fast and high-quality visual grounding, enabling precise object localization, dense detection, and point-based localization across diverse domains in both Enterprise Intelligence and Physical AI.

    3.8B32K ctx nvidia-license
    31.2KMar 2026gguf
    • Related category
    • Similar size (3.8B vs 3.3B)
    vs
  10. h2oai logo

    h2o-lightning-4b

    h2oai·Vision

    ≈4.2 GB

    H2O-Lightning-4B is a 4B-parameter decision model from H2O.ai, built on Qwen/Qwen3.5-4B. It answers typed decision questions about a record (a document, a ticket, a policy, a conversation) and about images that come with the record (photos, screenshots, scanned documents, charts).

    4.5B256K ctx Apache 2.0
    26.2KOct 2026gguf
    • Related category
    • Similar size (4.5B vs 3.3B)
    • Commercial use OK
    vs
  11. tencent logo

    WeVisOne-VL-4B

    tencent·Vision

    ≈4.5 GB

    WeVisOne-VL (WeChat Vision All-in-One) is a unified vision-language model developed by WeChat Vision, Tencent Inc. Built upon Qwen3-VL, it unifies object-level perception (open-vocabulary object detection, referring localization, object counting, object pointing, and OCR) and pixel-level perception…

    4.8B256K ctx Apache 2.0
    35.8KOct 2026gguf
    • Related category
    • Similar size (4.8B vs 3.3B)
    • Commercial use OK
    vs
  12. 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 3.3B)
    • Commercial use OK
    vs
  13. tencent logo

    WeVisOne-VL-2B

    tencent·Vision

    ≈2.8 GB

    WeVisOne-VL (WeChat Vision All-in-One) is a unified vision-language model developed by WeChat Vision, Tencent Inc. Built upon Qwen3-VL, it unifies object-level perception (open-vocabulary object detection, referring localization, object counting, object pointing, and OCR) and pixel-level perception…

    2.4B256K ctx Apache 2.0
    18.2KOct 2026gguf
    • Related category
    • Similar size (2.4B vs 3.3B)
    • Commercial use OK
    vs
  14. google logo

    gemma-3-4b-it

    google·Vision

    ≈3.7 GB

    Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.

    4.3B128K ctx Gemma Terms of Use
    1MFeb 2025ollama
    • Related category
    • Similar size (4.3B vs 3.3B)
    vs
  15. google logo

    medgemma-4b-it

    google·Vision

    ≈4.1 GB

    This section describes the MedGemma model and how to use it.

    4.3B128K ctx health-ai-developer-foundations
    470.4KMay 2025ollama
    • Related category
    • Similar size (4.3B vs 3.3B)
    vs
  16. CohereLabs logo

    North-Micro-Vision-Instruct

    CohereLabs·Vision

    ≈2.9 GB

    North Micro Vision Instruct is a 2.4B-parameter open-weight vision-language model with native-resolution image support, released under the Apache 2.0 license. It is designed as a compact foundation for prototyping, task-specific fine-tuning, and specialized multimodal applications.

    2.5B500K ctx Apache 2.0
    16.3KAug 2026
    • Related category
    • Similar size (2.5B vs 3.3B)
    • Commercial use OK
    vs
  17. ibm-granite logo

    granite-vision-3.3-2b

    ibm-granite·Vision

    ≈2.9 GB

    Model Summary: Granite-vision-3.3-2b is a compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.

    3B128K ctx Apache 2.0
    80.7KJun 2025gguf
    • Related category
    • Similar size (3B vs 3.3B)
    • Commercial use OK
    vs
  18. OpenGVLab logo

    InternVL2_5-4B-MPO

    OpenGVLab·Vision

    ≈3.0 GB

    We introduce InternVL2.5-MPO, an advanced multimodal large language model (MLLM) series that demonstrates superior overall performance. This series builds upon InternVL2.5 and Mixed Preference Optimization.

    3.7B32K ctx MIT
    245.8KDec 2024gguf
    • Related category
    • Similar size (3.7B vs 3.3B)
    • Commercial use OK
    vs
  19. openbmb logo

    MiniCPM-V-4.7-1B

    openbmb·Vision

    ≈1.8 GB

    MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 1B variant. It builds on the family's single-image, multi-image, and video understanding capabilities, combining stronger foundation capabilities with efficient visual encoding and on-device inference.

    1.6B256K ctx Apache 2.0
    468.2KOct 2026gguf
    • Related category
    • Smaller (1.6B vs 3.3B)
    • Commercial use OK
    vs
  20. internlm logo

    Intern-Decision-4B

    internlm·Vision

    ≈4.2 GB

    Intern-Decision-4B is a multimodal structured decision model fine-tuned from Qwen3.5-4B. It accepts a shared state, a schema of named questions, and optional images, and returns an answer distribution for every question in one model forward pass.

    4.5B256K ctx Apache 2.0
    5.9KSept 2026gguf
    • Related category
    • Similar size (4.5B vs 3.3B)
    • Commercial use OK
    vs
  21. Qwen logo

    Qwen-Drive-1.0-4B

    Qwen·Vision

    ≈4.0 GB

    Qwen-Drive-1.0 retains the architecture of the pretrained Qwen3.5 vision-language model and integrates 3D perception, visual question answering, and motion planning within a unified framework.

    4.5BApache 2.0
    6.7KAug 2026gguf
    • Related category
    • Similar size (4.5B vs 3.3B)
    • Commercial use OK
    vs
  22. microsoft logo

    Mage-VL-Cowork

    microsoft·Vision

    ≈4.4 GB

    Mage-VL-Cowork A Full Training Recipe to Learn Hybrid Computer Use from Evolved Harnesses

    4.7B256K ctx Apache 2.0
    5.7KOct 2026gguf
    • Related category
    • Similar size (4.7B vs 3.3B)
    • Commercial use OK
    • Newer release
    vs
  23. LiquidAI logo

    LFM3-VL-2B

    LiquidAI·Vision

    ≈2.0 GB

    LFM3-VL-2B is a vision-language model for on-device visual understanding. It takes text, images, and video as input, and combines the LFM3 language model with a new in-house vision encoder.

    1.9B125K ctx lfm1.0
    29.8KOct 2026ollama
    • Related category
    • Similar size (1.9B vs 3.3B)
    vs
  24. google logo

    gemma-3-4b-pt

    google·Vision

    ≈3.7 GB

    Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.

    4.3BGemma Terms of Use
    175.8KFeb 2025gguf
    • Related category
    • Similar size (4.3B vs 3.3B)
    vs