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. LiquidAI logo

    LFM2.5-VL-1.6B-Extract

    LiquidAI·Vision

    ≈1.7 GB

    LFM2.5-VL-1.6B-Extract extracts user-defined fields from images and returns them as JSON. It is Liquid AI's first vision model in the Liquid Nanos collection—compact, task-specific models built for production workflows—and extends the Extract family alongside LFM2-1.2B-Extract for text documents.

    1.6B125K ctx lfm1.0
    2.2KMay 2026gguf
    • Same category
    • Similar size (1.6B vs 1.9B)
    vs
  2. Qwen logo

    Qwen3.5-0.8B-Base

    Qwen·Vision

    ≈1.4 GB

    Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.

    873M256K ctx Apache 2.0
    880.7KFeb 2026gguf
    • Same category
    • Smaller (873M vs 1.9B)
    • Commercial use OK
    vs
  3. Qwen logo≈4.3 GB

    Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.

    4.4B256K ctx Apache 2.0
    2.8MOct 2025ollama
    • Same category
    • Larger (4.4B vs 1.9B)
    • Commercial use OK
    • Widely used
    vs
  4. inclusionAI logo

    UI-Venus-1.5-2B

    inclusionAI·Vision

    ≈2.8 GB

    This repository contains the UI-Venus model from the report UI-Venus-1.5 Technical Report. UI-Venus 1.5 is a unified, end-to-end GUI Agent designed for robust real-world applications. The model family includes two dense (2B/8B) and one MoE (30B-A3B) variants to meet various downstream scenarios.

    2.4B256K ctx Apache 2.0
    3.6KFeb 2026gguf
    • Same category
    • Similar size (2.4B vs 1.9B)
    • Commercial use OK
    vs
  5. LiquidAI logo

    LFM2-VL-1.6B

    LiquidAI·Vision

    ≈1.7 GB

    LFM2‑VL is Liquid AI's first series of multimodal models, designed to process text and images with variable resolutions. Built on the LFM2 backbone, it is optimized for low-latency and edge AI applications.

    1.6B125K ctx lfm1.0
    9.2KAug 2025gguf
    • Same category
    • Similar size (1.6B vs 1.9B)
    vs
  6. apple logo

    FastVLM-1.5B

    apple·Vision

    ≈1.9 GB

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

    1.9B32K ctx Apple Machine Learning Research License
    1.2KAug 2025
    • Same category
    • Similar size (1.9B vs 1.9B)
    vs
  7. OpenGVLab logo

    InternVL3_5-2B

    OpenGVLab·Vision

    ≈2.8 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.

    2.3B40K ctx Apache 2.0
    6.5KAug 2025gguf
    • Same category
    • Similar size (2.3B vs 1.9B)
    • Commercial use OK
    vs
  8. NemoStation logo

    Marlin-2B

    NemoStation·Vision

    ≈2.4 GB

    Marlin: a tiny VLM to extract structured information from videos

    2.2BApache 2.0
    434May 2026gguf
    • Same category
    • Similar size (2.2B vs 1.9B)
    • Commercial use OK
    vs
  9. tencent logo

    Penguin-VL-2B

    tencent·Vision

    ≈2.7 GB

    Penguin-VL Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders

    2.2B40K ctx Apache 2.0
    642Mar 2026
    • Same category
    • Similar size (2.2B vs 1.9B)
    • Commercial use OK
    vs
  10. 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
    • Same category
    • Similar size (3.8B vs 1.9B)
    • Widely used
    vs
  11. 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
    78.8KJun 2025gguf
    • Same category
    • Similar size (3B vs 1.9B)
    • Commercial use OK
    vs
  12. h2oai logo≈2.2 GB

    The H2OVL-Mississippi-2B is a high-performing, general-purpose vision-language model developed by H2O.ai to handle a wide range of multimodal tasks.

    2.2B8K ctx Apache 2.0
    20.3KOct 2024gguf
    • Same category
    • Similar size (2.2B vs 1.9B)
    • Commercial use OK
    vs
  13. 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
    496.7KFeb 2026gguf
    • Same category
    • Larger (4.7B vs 1.9B)
    • Commercial use OK
    vs
  14. 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
    67.8KApr 2026gguf
    • Same category
    • Larger (4B vs 1.9B)
    • Commercial use OK
    vs
  15. 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
    • Same category
    • Smaller (957M vs 1.9B)
    • Commercial use OK
    vs
  16. 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
    183.5KJan 2026ollama
    • Same category
    • Larger (4.3B vs 1.9B)
    vs
  17. 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
    31.3KMar 2026gguf
    • Same category
    • Similar size (3.8B vs 1.9B)
    vs
  18. 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
    26.1KOct 2026gguf
    • Same category
    • Larger (4.5B vs 1.9B)
    • Commercial use OK
    vs
  19. 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
    36.4KOct 2026gguf
    • Same category
    • Larger (4.8B vs 1.9B)
    • Commercial use OK
    • Newer release
    vs
  20. 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
    1.1MFeb 2025ollama
    • Same category
    • Larger (4.3B vs 1.9B)
    vs
  21. 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
    469.7KMay 2025ollama
    • Same category
    • Larger (4.3B vs 1.9B)
    vs
  22. 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
    • Same category
    • Similar size (1.1B vs 1.9B)
    • Commercial use OK
    vs
  23. google logo

    paligemma-3b-pt-224

    google·Vision

    ≈2.4 GB

    Transformers PaliGemma 3B weights, pre-trained with 224*224 input images and 128 token input/output text sequences. The models are available in float32, bfloat16 and float16 formats for fine-tuning.

    2.9BGemma Terms of Use
    226.8KMay 2024
    • Same category
    • Similar size (2.9B vs 1.9B)
    vs
  24. 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
    • Same category
    • Similar size (1.1B vs 1.9B)
    • Commercial use OK
    vs