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 Mage-VL-Cowork

120 open-weight models that do the same job as Mage-VL-Cowork (4.7B 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
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
--vram
any
--gpus
--quant
  1. 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
    • Same category
    • Similar size (4.5B vs 4.7B)
    vs
  2. LiquidAI logo

    LFM2.5-VL-3B

    LiquidAI·Vision

    ≈2.8 GB

    LFM2.5-VL-3B is a multimodal variant of LFM2.5, a family of hybrid models designed for on-device deployment. It builds on LFM2-VL-3B with further mid- and post-training.

    3.1B32K ctx lfm1.0
    54.2KAug 2026gguf
    • Same category
    • Similar size (3.1B vs 4.7B)
    vs
  3. GroundingPI logo

    GroundingPI

    GroundingPI·Vision

    ≈4.5 GB

    Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control.

    4.8B256K ctx apache-2.0-with-upstream-kimi-k3
    956Sept 2026
    • Same category
    • Similar size (4.8B vs 4.7B)
    • Commercial use OK
    vs
  4. OpenGVLab logo

    InternVL3_5-4B

    OpenGVLab·Vision

    ≈4.4 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.

    4.7B40K ctx Apache 2.0
    16.2KAug 2025gguf
    • Same category
    • Similar size (4.7B vs 4.7B)
    • Commercial use OK
    vs
  5. 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
    116KFeb 2025gguf
    • Same category
    • Similar size (4.3B vs 4.7B)
    vs
  6. allenai logo

    MolmoWeb-4B

    allenai·Vision

    ≈4.5 GB

    Important Update! We made a few small but important updates to this HF/transformers-compatible checkpoint to ensure exact outputs to our native model checkpoint on March 29, 2026 ~6PM PST. If you downloaded this model checkpoint earlier than this time, we recommend re-downloading it.

    4.9B10K ctx Apache 2.0
    2.4KMar 2026
    • Same category
    • Similar size (4.9B vs 4.7B)
    • Commercial use OK
    vs
  7. docling-project logo

    DeskForge-Qwen3.5-4B

    docling-project·Vision

    ≈4.2 GB

    DeskForge-Qwen3.5-4B is Qwen3.5-4B fine-tuned for desktop GUI grounding and next-action prediction using grounding and GUI-workflow supervision.

    4.5B256K ctx Apache 2.0
    623Sept 2026gguf
    • Same category
    • Similar size (4.5B vs 4.7B)
    • Commercial use OK
    vs
  8. 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
    19.1KOct 2026gguf
    • Same category
    • Similar size (3.1B vs 4.7B)
    vs
  9. Qwen logo≈5.8 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.

    8.3B125K ctx Apache 2.0
    5.2MJan 2025ollama
    • Same category
    • Similar size (8.3B vs 4.7B)
    • Commercial use OK
    • Widely used
    vs
  10. inclusionAI logo

    ZwZ-4B

    inclusionAI·Vision

    ≈4.5 GB

    ZwZ-4B is a fine-grained multimodal perception model built upon Qwen3-VL-4B. It is trained using Region-to-Image Distillation (R2I) combined with reinforcement learning, enabling superior fine-grained visual understanding in a single forward pass — no inference-time zooming or tool calling…

    4.8B256K ctx Apache 2.0
    1.6KFeb 2026gguf
    • Same category
    • Similar size (4.8B vs 4.7B)
    • Commercial use OK
    vs
  11. openbmb logo

    MiniCPM-V-4

    openbmb·Vision

    ≈3.2 GB

    A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

    4.1B32K ctx Apache 2.0
    30.4KJul 2025gguf
    • Same category
    • Similar size (4.1B vs 4.7B)
    • Commercial use OK
    vs
  12. 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
    90.3KAug 2026
    • Same category
    • Similar size (2.6B vs 4.7B)
    • Commercial use OK
    vs
  13. microsoft logo

    Phi-3.5-vision-instruct

    microsoft·Vision

    ≈6.0 GB

    Phi-3.5-vision 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
    237.6KAug 2024
    • Same category
    • Similar size (4.1B vs 4.7B)
    • Commercial use OK
    vs
  14. 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 4.7B)
    • Commercial use OK
    vs
  15. ibm-granite logo

    granite-4.0-3b-vision

    ibm-granite·Vision

    ≈3.5 GB

    Model Summary: Granite-4.0-3B-Vision is a vision-language model (VLM) designed for enterprise-grade document data extraction. It focuses on specialized, complex extraction tasks that ultracompact models often struggle with:

    4B128K ctx Apache 2.0
    3.3KMar 2026gguf
    • Same category
    • Similar size (4B vs 4.7B)
    • Commercial use OK
    vs
  16. Zyphra logo

    ZAYA1-VL-8B

    Zyphra·Vision

    ≈6.6 GB

    ZAYA1-VL-8B is a vision-language model (VLM) built upon Zyphra's ZAYA1-8B LLM. It has state-of-the-art performance among VLMs for its size and inference efficiency.

    9.7B32K ctx Apache 2.0
    339.4KApr 2026gguf
    • Same category
    • Larger (9.7B vs 4.7B)
    • Commercial use OK
    vs
  17. stepfun-ai logo

    GELab-Zero-4B-preview

    stepfun-ai·Vision

    ≈4.3 GB

    This model is part of the GELab-Zero project, which presents the Step-GUI Technical Report [Paper] [Project Page] [Code].

    4.4B256K ctx Apache 2.0
    2.3KNov 2025gguf
    • Same category
    • Similar size (4.4B vs 4.7B)
    • Commercial use OK
    vs
  18. 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
    475.6KDec 2025gguf
    • Same category
    • Similar size (2.4B vs 4.7B)
    • Commercial use OK
    vs
  19. 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
    • Same category
    • Smaller (2.3B vs 4.7B)
    • Commercial use OK
    vs
  20. Qwen logo

    Qwen3.5-9B-Base

    Qwen·Vision

    ≈7.2 GB

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

    9.7B256K ctx Apache 2.0
    266.8KFeb 2026gguf
    • Same category
    • Larger (9.7B vs 4.7B)
    • Commercial use OK
    vs
  21. 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 4.7B)
    vs
  22. 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
    • Similar size (9.4B vs 4.7B)
    • Commercial use OK
    vs
  23. 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
    • Similar size (9.4B vs 4.7B)
    • Commercial use OK
    vs
  24. 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
    • Similar size (9.4B vs 4.7B)
    • Commercial use OK
    vs