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 ZwZ2-4B

120 open-weight models that do the same job as ZwZ2-4B (4.5B 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
inclusionAI logo

ZwZ2-4B

inclusionAI·Vision

≈4.2 GB

ZwZ2-4B is the Qwen3.5-4B-based model in Zooming-without-Zooming-v2 (ZwZ2). It learns to connect visual evidence across regions through comparison, aggregation, matching, and multi-step reasoning. Training uses full images; inference requires no zooming tools.

4.5B256K ctx Unknown licence
1.1KOct 2026gguf
--vram
any
--gpus
--quant
  1. tencent logo

    Youtu-VL-4B-Instruct

    tencent·Vision

    ≈6.2 GB

    Youtu-VL is a lightweight yet robust Vision-Language Model (VLM) built on the Youtu-LLM with 4B parameters. It pioneers Vision-Language Unified Autoregressive Supervision (VLUAS), which markedly strengthens visual perception and multimodal understanding.

    5.3B32K ctx youtu-vl
    1.4KJan 2026gguf
    • Same category
    • Similar size (5.3B vs 4.5B)
    vs
  2. XiaomiMiMo logo

    MiMo-V2.6-Distill-Qwen-9B

    XiaomiMiMo·Vision

    ≈7.1 GB

    MiMo-V2.6-Distill-Qwen-9B is a 9B agentic model developed by Xiaomi MiMo through supervised fine-tuning of Qwen3.5-9B on MiMo-generated data. It covers coding, general-purpose agent tasks, visual coding, and cybersecurity.

    9.4B256K ctx MIT
    38.9KSept 2026gguf
    • Same category
    • Larger (9.4B vs 4.5B)
    • Commercial use OK
    vs
  3. black-forest-labs logo

    flux-3-image-klein-pup

    black-forest-labs·Vision

    ≈7.1 GB

    FLUX 3 Image Klein Prompt Upsampler is a 9B vision-language model that expands a short image request into the detailed prompt FLUX 3 Image Klein works best with. It takes the request, up to 10 reference images and an optional list of bounding boxes, and returns one prompt.

    9.4B256K ctx Apache 2.0
    31KOct 2026gguf
    • Same category
    • Larger (9.4B vs 4.5B)
    • Commercial use OK
    vs
  4. Cloudflare logo

    clef-flash

    Cloudflare·Vision

    ≈7.1 GB

    Clef-Flash is a 9B multimodal model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question in a single forward pass.

    9.4B256K ctx Apache 2.0
    32.7KSept 2026ollama
    • Same category
    • Larger (9.4B vs 4.5B)
    • Commercial use OK
    vs
  5. 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 4.5B)
    • Commercial use OK
    vs
  6. omlab logo

    VLX-Seek-1.5-10B

    omlab·Vision

    ≈7.4 GB

    VLX-Seek-1.5-10B is the open-source 10B model in the VLX-Seek 1.5 family, designed for fine-grained perception and visual grounding in embodied scenarios.

    10B256K ctx Apache 2.0
    73.4KJul 2026gguf
    • Same category
    • Larger (10B vs 4.5B)
    • Commercial use OK
    vs
  7. tencent logo

    HY-Embodied-0.5

    tencent·Vision

    ≈3.2 GB

    We introduce HY-Embodied-0.5, a suite of foundation models tailored specifically for real-world embodied intelligence. To bridge the gap between general Vision-Language Models (VLMs) and the strict demands of physical agents, our models are engineered to excel in spatial-temporal visual perception…

    3.8B256K ctx Custom licence
    597Apr 2026
    • Same category
    • Similar size (3.8B vs 4.5B)
    vs
  8. internlm logo

    CapRL-3B

    internlm·Vision

    ≈3.0 GB

    We are excited to release the CapRL 2.0 series: CapRL-Qwen3VL-2B and CapRL-Qwen3VL-4B. These models feature fewer parameters while delivering even more powerful captioning performance. Notably, CapRL-Qwen3VL-2B outperforms both CapRL-Qwen2.5VL-3B and Qwen2.5VL-72B in captioning tasks.

    3.8B125K ctx Apache 2.0
    2.5KSept 2025gguf
    • Same category
    • Similar size (3.8B vs 4.5B)
    • Commercial use OK
    vs
  9. 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
    • Same category
    • Smaller (1.6B vs 4.5B)
    • Commercial use OK
    vs
  10. allenai logo

    Molmo2-O-7B

    allenai·Vision

    ≈9.1 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.

    7.8B64K ctx Apache 2.0
    28KDec 2025gguf
    • Same category
    • Similar size (7.8B vs 4.5B)
    • Commercial use OK
    vs
  11. microsoft logo≈6.0 GB

    The Phi-3-Vision-128K-Instruct is a lightweight, state-of-the-art open multimodal model built upon datasets which include - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data both on text and vision.

    4.1B128K ctx MIT
    38.2KMay 2024
    • Same category
    • Similar size (4.1B vs 4.5B)
    • Commercial use OK
    vs
  12. Qwen logo≈6.8 GB

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

    8.8B256K ctx Apache 2.0
    136.3KOct 2025gguf
    • Same category
    • Similar size (8.8B vs 4.5B)
    • Commercial use OK
    vs
  13. Salesforce logo

    blip2-opt-2.7b

    Salesforce·Vision

    ≈5.2 GB

    BLIP-2 model, leveraging OPT-2.7b (a large language model with 2.7 billion parameters). It was introduced in the paper BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models by Li et al. and first released in this repository.

    3.7BMIT
    379.4KFeb 2023
    • Same category
    • Similar size (3.7B vs 4.5B)
    • Commercial use OK
    vs
  14. 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 4.5B)
    • Commercial use OK
    • Newer release
    vs
  15. allenai logo

    Molmo2-8B

    allenai·Vision

    ≈6.8 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.

    8.7B36K ctx Apache 2.0
    54.4KDec 2025gguf
    • Same category
    • Similar size (8.7B vs 4.5B)
    • Commercial use OK
    vs
  16. ByteDance-Seed logo

    UI-TARS-1.5-7B

    ByteDance-Seed·Vision

    ≈5.8 GB

    We shared the latest progress of the UI-TARS-1.5 model in our blog, which excels in playing games and performing GUI tasks.

    8.3B125K ctx Apache 2.0
    228.5KApr 2025gguf
    • Same category
    • Similar size (8.3B vs 4.5B)
    • Commercial use OK
    vs
  17. nvidia logo

    Cosmos-Reason2-8B

    nvidia·Vision

    ≈6.8 GB

    NVIDIA Cosmos Reason 2 is an open, customizable, 8B-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.

    8.8B256K ctx NVIDIA Open Model License
    59KDec 2025gguf
    • Same category
    • Similar size (8.8B vs 4.5B)
    • Commercial use OK
    vs
  18. huihui-ai logo≈5.8 GB

    This is an uncensored version of Qwen/Qwen2.5-VL-7B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it).

    8.3B125K ctx Apache 2.0
    308.9KFeb 2025gguf
    • Same category
    • Similar size (8.3B vs 4.5B)
    • Commercial use OK
    vs
  19. OpenGVLab logo

    InternVL3_5-8B

    OpenGVLab·Vision

    ≈6.7 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.

    8.5B40K ctx Apache 2.0
    95.6KAug 2025gguf
    • Same category
    • Similar size (8.5B vs 4.5B)
    • Commercial use OK
    vs
  20. 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
    • Same category
    • Smaller (1.9B vs 4.5B)
    • Newer release
    vs
  21. deepseek-ai logo

    deepseek-vl2-tiny

    deepseek-ai·Vision

    ≈2.7 GB

    Introducing DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL.

    3.4BA1.2B4K ctx DeepSeek License
    28KDec 2024
    • Same category
    • Similar size (3.4B vs 4.5B)
    vs
  22. swiss-ai logo

    Apertus-v1.5-8B

    swiss-ai·Vision

    ≈6.9 GB

    Apertus 1.5 is a family of 8B and 70B parameter language models designed to advance the state of multilingual, multimodal, fully open, and transparent AI.

    8.9BApache 2.0
    9.4KJul 2026gguf
    • Same category
    • Similar size (8.9B vs 4.5B)
    • Commercial use OK
    vs
  23. inclusionAI logo

    UI-Venus-2-9B

    inclusionAI·Vision

    ≈6.8 GB

    UI-Venus-2 is a general-purpose foundation GUI agent designed to operate across mobile applications, web platforms, and desktop operating systems through a unified closed-loop reasoning–action framework: the agent observes the current interface, reasons about the task state, executes an action, and…

    9B256K ctx Unknown licence
    6.5KAug 2026gguf
    • Same category
    • Similar size (9B vs 4.5B)
    vs
  24. nvidia logo≈6.7 GB

    Llama Nemotron Nano VL is a leading document intelligence vision language model (VLMs) that enables the ability to query and summarize images from the physical or virtual world.

    8.7B128K ctx NVIDIA Open Model License
    154.4KJun 2025
    • Same category
    • Similar size (8.7B vs 4.5B)
    • Commercial use OK
    vs