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 OvisOCR3

120 open-weight models that do the same job as OvisOCR3 (853M 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
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
437.7KOct 2026gguf
--vram
any
--gpus
--quant
  1. nvidia logo≈1.4 GB

    NVIDIA Nemotron Parse v1.1 is designed to understand document semantics and extract text and tables elements with spatial grounding.

    957M9K ctx NVIDIA Open Model License
    110.8KNov 2025
    • Related category
    • Similar size (957M vs 853M)
    • Commercial use OK
    vs
  2. 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
    468.8KOct 2026gguf
    • Related category
    • Similar size (1.6B vs 853M)
    • Commercial use OK
    vs
  3. nvidia logo

    Nemotron-3.5-Parse

    nvidia·Vision

    ≈1.2 GB

    Nemotron 3.5 Parse is a document image parser that produces structured, machine-readable text with semantic layout classes, bounding boxes, and reading order. It combines a C-RADIOv4-SO400M vision encoder with a 10-layer mBART decoder that consumes the visual sequence as a causal prefix.

    631M16K ctx Custom licence
    26.5KSept 2026gguf
    • Related category
    • Similar size (631M vs 853M)
    • Commercial use OK
    vs
  4. google logo

    t5gemma-2-270m-270m

    google·Vision

    ≈1.1 GB

    T5Gemma is a family of lightweight yet powerful encoder-decoder research models from Google, built by adapting pretrained decoder-only Gemma models into encoder-decoder ones.

    786M32K ctx Gemma Terms of Use
    32.2KOct 2025
    • Related category
    • Similar size (786M vs 853M)
    vs
  5. openbmb logo

    MiniCPM-V-4.6

    openbmb·Vision

    ≈1.6 GB

    A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

    1.3B256K ctx Apache 2.0
    194.5KApr 2026ollama
    • Related category
    • Similar size (1.3B vs 853M)
    • Commercial use OK
    vs
  6. nvidia logo≈1.4 GB

    NVIDIA Nemotron Parse v1.2 is designed to understand document semantics and extract text and tables elements with spatial grounding.

    936M9K ctx NVIDIA Open Model License
    10.2KFeb 2026
    • Related category
    • Similar size (936M vs 853M)
    • Commercial use OK
    vs
  7. OpenGVLab logo

    InternVL3-1B-hf

    OpenGVLab·Vision

    ≈1.1 GB

    We introduce InternVL3, an advanced multimodal large language model (MLLM) series that demonstrates superior overall performance.

    938M32K ctx Qwen License
    72.4KApr 2025
    • Related category
    • Similar size (938M vs 853M)
    vs
  8. apple logo

    FastVLM-0.5B

    apple·Vision

    ≈1.0 GB

    FastVLM was introduced in FastVLM: Efficient Vision Encoding for Vision Language Models. (CVPR 2025)

    759M32K ctx Apple Machine Learning Research License
    22.4KAug 2025gguf
    • Related category
    • Similar size (759M vs 853M)
    vs
  9. OpenGVLab logo

    InternVL3-1B

    OpenGVLab·Vision

    ≈1.1 GB

    We introduce InternVL3, an advanced multimodal large language model (MLLM) series that demonstrates superior overall performance.

    938M32K ctx Apache 2.0
    54.6KApr 2025gguf
    • Related category
    • Similar size (938M vs 853M)
    • Commercial use OK
    vs
  10. llava-hf logo≈1.1 GB

    Check out also the Google Colab demo to run Llava on a free-tier Google Colab instance:

    894MApache 2.0
    187.7KAug 2024
    • Related category
    • Similar size (894M vs 853M)
    • Commercial use OK
    vs
  11. LiquidAI logo

    d1-omni-600M

    LiquidAI·Omni

    ≈1.1 GB

    d1-omni-600M is a 600M parameter decision model built on LFM2.5-Encoder-350M. You give it a state (text or JSON, with images or a voice clip) and a set of named questions.

    587M125K ctx lfm1.0
    7.7KOct 2026gguf
    • Related category
    • Similar size (587M vs 853M)
    vs
  12. openbmb logo

    MiniCPM-V-4.6-Thinking

    openbmb·Vision

    ≈1.6 GB

    A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

    1.3B256K ctx Apache 2.0
    27.1KMay 2026gguf
    • Related category
    • Similar size (1.3B vs 853M)
    • Commercial use OK
    vs
  13. PaddlePaddle logo

    HPD-Parsing

    PaddlePaddle·Vision

    ≈2.0 GB

    🎉 A live demo is available at hugging-apps/hpd-parsing. Thanks to multimodalart for building it! 🚀 We release HPD-Parsing, a 1B hierarchical parallel document parser. It achieves 94.91% overall on OmniDocBench v1.6 and 4,752 TPS peak throughput.

    1.1B40K ctx Apache 2.0
    2.3KJul 2026
    • Related category
    • Similar size (1.1B vs 853M)
    • Commercial use OK
    vs
  14. 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
    • Larger (2.3B vs 853M)
    • Commercial use OK
    • Widely used
    vs
  15. inclusionAI logo

    SingGuard-NSFA-0.8B

    inclusionAI·Vision

    ≈1.5 GB

    SingGuard-NSFA is a dual-mode guardrail framework for securing agentic AI systems against operational threats such as prompt injection, sensitive information extraction, malicious code requests, dangerous tool misuse, and resource exhaustion.

    1.1B256K ctx Apache 2.0
    1.8KJul 2026
    • Related category
    • Similar size (1.1B vs 853M)
    • Commercial use OK
    vs
  16. h2oai logo≈1.4 GB

    The H2OVL-Mississippi-800M is a compact yet powerful vision-language model from H2O.ai, featuring 0.8 billion parameters. Despite its small size, it delivers state-of-the-art performance in text recognition, excelling in the Text Recognition segment of OCRBench and outperforming much larger models…

    826M8K ctx Apache 2.0
    27.3KOct 2024gguf
    • Related category
    • Similar size (826M vs 853M)
    • Commercial use OK
    vs
  17. OpenGVLab logo

    InternVL3_5-1B

    OpenGVLab·Vision

    ≈2.0 GB

    We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series.

    1.1B40K ctx Apache 2.0
    12.9KAug 2025gguf
    • Related category
    • Similar size (1.1B vs 853M)
    • Commercial use OK
    vs
  18. llava-hf logo≈1.8 GB

    Model type: LLaVA Interleave is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. Base LLM: Qwen/Qwen1.5-7B-Chat

    864M32K ctx Qwen Research License
    17.9KJul 2024
    • Related category
    • Similar size (864M vs 853M)
    vs
  19. LiquidAI logo

    LFM2.5-VL-450M

    LiquidAI·Vision

    ≈1.0 GB

    LFM2.5‑VL-450M is Liquid AI's refreshed version of the first vision-language model, LFM2-VL-450M, built on an updated backbone LFM2.5-350M and tuned for stronger real-world performance. Find more about LFM2.5 family of models in our blog post.

    449M125K ctx lfm1.0
    41.4KApr 2026gguf
    • Related category
    • Similar size (449M vs 853M)
    vs
  20. opendatalab logo

    MinerU-HTML

    opendatalab·Chat

    ≈1.8 GB

    Dripper(MinerU-HTML) is an advanced HTML main content extraction tool based on Large Language Models (LLMs). It provides a complete pipeline for extracting primary content from HTML pages using LLM-based classification and state machine-guided generation.

    752M40K ctx Apache 2.0
    687Nov 2025gguf
    • Related category
    • Similar size (752M vs 853M)
    • Commercial use OK
    vs
  21. 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
    30.7KOct 2026ollama
    • Related category
    • Larger (1.9B vs 853M)
    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
    • Larger (2.1B vs 853M)
    • Commercial use OK
    vs
  23. LiquidAI logo

    d1-2B

    LiquidAI·Vision

    ≈2.0 GB

    d1-2B is a decision model for text, pictures, and video, built on LFM3-VL-2B. It returns calibrated answers in one forward pass, without generating tokens.

    1.9B125K ctx lfm1.0
    17.1KOct 2026ollama
    • Related category
    • Larger (1.9B vs 853M)
    • Newer release
    vs
  24. 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
    • Larger (2.3B vs 853M)
    • Commercial use OK
    vs