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 LFM3-VL-2B

120 open-weight models that do the same job as LFM3-VL-2B (1.9B vision), 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
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
--vram
any
--gpus
--quant
  1. tencent logo

    Youtu-Parsing

    tencent·Vision

    ≈3.0 GB

    Youtu-Parsing is a specialized document parsing model built upon the open-source Youtu-LLM 2B foundation. By extending the capabilities of the base model with a prompt-guided framework and NaViT-style dynamic visual encoder, Youtu-Parsing offers enhanced parsing capabilities for diverse document…

    2.5B20K ctx youtu-parsing
    428Jan 2026
    • Same category
    • Similar size (2.5B vs 1.9B)
    vs
  2. LiquidAI logo

    LFM2-VL-3B

    LiquidAI·Vision

    ≈2.8 GB

    LFM2-VL-3B is the newest and most capable model in Liquid AI's multimodal LFM2-VL series, designed to process text and images with variable resolutions. Built on the LFM2 backbone, it extends the architecture for higher-capacity reasoning and stronger visual understanding while retaining efficiency.

    3B125K ctx lfm1.0
    3.6KOct 2025gguf
    • Same category
    • Similar size (3B vs 1.9B)
    vs
  3. 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
    245.9KDec 2024gguf
    • Same category
    • Similar size (3.7B vs 1.9B)
    • Commercial use OK
    vs
  4. microsoft logo

    GUI-Actor-2B-Qwen2-VL

    microsoft·Vision

    ≈2.0 GB

    This model was introduced in the paper GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents. It is developed based on Qwen2-VL-2B-Instruct , augmented by an attention-based action head and finetuned to perform GUI grounding using the dataset here.

    2.2B32K ctx MIT
    556Jun 2025
    • Same category
    • Similar size (2.2B vs 1.9B)
    • Commercial use OK
    vs
  5. tencent logo

    WeMM-Video-2B

    tencent·Vision

    ≈2.8 GB

    WeMM-Video-2B is the dense 2B checkpoint in the WeMM-Video family. WeMM-Video is a Chinese–English bilingual family for joint audio-visual understanding and reasoning. It accepts text, images, audio, and video and generates text responses.

    3.3B256K ctx Apache 2.0
    259Nov 2026gguf
    • Same category
    • Similar size (3.3B vs 1.9B)
    • Commercial use OK
    • Newer release
    vs
  6. ByteDance-Seed logo

    UI-TARS-2B-SFT

    ByteDance-Seed·Vision

    ≈2.2 GB

    UI-TARS is a next-generation native GUI agent model designed to interact seamlessly with graphical user interfaces (GUIs) using human-like perception, reasoning, and action capabilities.

    2.4B32K ctx Apache 2.0
    2.8KJan 2025gguf
    • Same category
    • Similar size (2.4B vs 1.9B)
    • Commercial use OK
    vs
  7. jinaai logo

    jina-vlm

    jinaai·Vision

    ≈2.4 GB

    jina-vlm is a token-efficient 2.4B parameter vision-language model that achieves state-of-the-art multilingual VQA performance among open 2B-scale VLMs.

    2.5B40K ctx CC BY-NC 4.0
    308Nov 2025
    • Same category
    • Similar size (2.5B vs 1.9B)
    vs
  8. 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
    • Same category
    • Smaller (936M vs 1.9B)
    • Commercial use OK
    vs
  9. 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
    • Same category
    • Similar size (1.1B vs 1.9B)
    • Commercial use OK
    vs
  10. deepseek-ai logo

    deepseek-vl-1.3b-chat

    deepseek-ai·Vision

    ≈3.2 GB

    Introducing DeepSeek-VL, an open-source Vision-Language (VL) Model designed for real-world vision and language understanding applications.

    2B16K ctx DeepSeek License
    4.1KMar 2024
    • Same category
    • Similar size (2B vs 1.9B)
    vs
  11. internlm logo

    Intern-Decision-0.8B

    internlm·Vision

    ≈1.4 GB

    Intern-Decision-0.8B is a multimodal structured decision model fine-tuned from Qwen3.5-0.8B. 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.

    853M256K ctx Apache 2.0
    4.1KSept 2026gguf
    • Same category
    • Smaller (853M vs 1.9B)
    • Commercial use OK
    vs
  12. 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
    • Same category
    • Larger (4.5B vs 1.9B)
    • Commercial use OK
    vs
  13. HuggingFaceTB logo

    SmolVLM-Base

    HuggingFaceTB·Vision

    ≈3.3 GB

    SmolVLM is a compact open multimodal model that accepts arbitrary sequences of image and text inputs to produce text outputs.

    2.2B16K ctx Apache 2.0
    1.5KNov 2024gguf
    • Same category
    • Similar size (2.2B vs 1.9B)
    • Commercial use OK
    vs
  14. nvidia logo

    DAM-3B

    nvidia·Vision

    ≈2.9 GB

    Describe Anything Model 3B (DAM-3B) takes inputs of user-specified regions in the form of points/boxes/scribbles/masks within images, and generates detailed localized descriptions of images.

    3Bnvidia-non-commercial-license
    6.9KApr 2025
    • Same category
    • Similar size (3B vs 1.9B)
    vs
  15. 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
    6.5KAug 2026gguf
    • Same category
    • Larger (4.5B vs 1.9B)
    • Commercial use OK
    vs
  16. google logo

    paligemma-3b-mix-224

    google·Vision

    ≈2.4 GB

    Transformers PaliGemma 3B weights, fine-tuned with 224*224 input images and 256 token input/output text sequences on a mixture of downstream academic datasets. The models are available in float32, bfloat16 and float16 format for research purposes only.

    2.9BGemma Terms of Use
    72.5KMay 2024
    • Same category
    • Similar size (2.9B vs 1.9B)
    vs
  17. 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
    • Same category
    • Smaller (938M vs 1.9B)
    vs
  18. 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
    5.8KOct 2026gguf
    • Same category
    • Larger (4.7B vs 1.9B)
    • Commercial use OK
    • Newer release
    vs
  19. google logo≈3.2 GB

    Transformers PaliGemma 2 3B weights, fine-tuned with 448*448 input images on the DOCCI dataset.

    3BGemma Terms of Use
    15.4KNov 2024
    • Same category
    • Similar size (3B vs 1.9B)
    vs
  20. google logo

    paligemma2-3b-mix-224

    google·Vision

    ≈3.2 GB

    Transformers PaliGemma 2 3B weights fine-tuned on a mixture of academic tasks using 224×224 input images. PaliGemma 2 mix checkpoints are fine-tuned on a diverse set of tasks and are ready to use out of the box while pt checkpoints are pre-trained and intended for further fine-tuning.

    3BGemma Terms of Use
    15.8KNov 2024
    • Same category
    • Similar size (3B vs 1.9B)
    vs
  21. 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
    • Same category
    • Smaller (938M vs 1.9B)
    • Commercial use OK
    vs
  22. OpenGVLab logo≈1.9 GB

    VideoChat-Flash-2B is constructed upon UMT-L (300M) and Qwen2.5-1.5B, employing only 16 tokens per frame. By leveraging Yarn to extend the context window to 128k (Qwen2's native context window is 32k), our model supports input sequences of up to approximately 10,000 frames.

    2.1B32K ctx Apache 2.0
    306Jan 2025
    • Same category
    • Similar size (2.1B vs 1.9B)
    • Commercial use OK
    vs
  23. facebook logo

    Perception-LM-1B

    facebook·Vision

    ≈1.9 GB

    Perception Language Model (PLM) is a state-of-the-art, fully open and reproducible MLLM for transparent research in image and video understanding. It was introduced in "PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding".

    1.5Bfair-noncommercial-research
    522Apr 2025
    • Same category
    • Similar size (1.5B vs 1.9B)
    vs
  24. allenai logo

    Molmo2-4B

    allenai·Vision

    ≈4.5 GB

    Molmo2 is a family of open vision-language models developed by the Allen Institute for AI (Ai2) that support image, video and multi-image understanding and grounding.

    4.9B36K ctx Apache 2.0
    46.2KDec 2025gguf
    • Same category
    • Larger (4.9B vs 1.9B)
    • Commercial use OK
    vs