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 Agnes-2.5-Pro-Theta

120 open-weight models that do the same job as Agnes-2.5-Pro-Theta (188B 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
Agnes-AI logo

Agnes-2.5-Pro-Theta

Agnes-AI·Vision

≈117 GB

Agnes 2.5 Pro Theta is a multimodal mixture-of-experts checkpoint distributed with its model implementation, tokenizer, chat template, and image/video processors. This release provides BF16 weights for local inference through Transformers.

188BApache 2.0
813Nov 2026
--vram
any
--gpus
--quant
  1. Qwen logo

    QVQ-72B-Preview

    Qwen·Vision

    ≈47 GB

    QVQ-72B-Preview is an experimental research model developed by the Qwen team, focusing on enhancing visual reasoning capabilities.

    73.4B125K ctx Qwen License
    1.7KDec 2024gguf
    • Same category
    • Smaller (73.4B vs 188B)
    vs
  2. Qwen logo≈22 GB

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

    36BA3B256K ctx Apache 2.0
    42KFeb 2026gguf
    • Same category
    • Smaller (36B vs 188B)
    • Commercial use OK
    vs
  3. Qwen logo≈22 GB

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

    33.4B256K ctx Apache 2.0
    217.3KOct 2025ollama
    • Same category
    • Smaller (33.4B vs 188B)
    • Commercial use OK
    vs
  4. Qwen logo≈20 GB

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

    31.1BA3B256K ctx Apache 2.0
    432.4KSept 2025ollama
    • Same category
    • Smaller (31.1B vs 188B)
    • Commercial use OK
    vs
  5. Cloudflare logo

    clef

    Cloudflare·Vision

    ≈19 GB

    Clef is a 27B 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.

    27.4B256K ctx Apache 2.0
    78.2KSept 2026ollama
    • Same category
    • Smaller (27.4B vs 188B)
    • Commercial use OK
    vs
  6. meta-llama logo≈56 GB

    The Llama 3.2-Vision collection of multimodal large language models (LLMs) is a collection of pretrained and instruction-tuned image reasoning generative models in 11B and 90B sizes (text \+ images in / text out).

    88.6B128K ctx Llama 3.2 Community License
    420Sept 2024ollama
    • Same category
    • Smaller (88.6B vs 188B)
    vs
  7. HuggingFaceM4 logo

    idefics-80b-instruct

    HuggingFaceM4·Vision

    ≈53 GB

    How do I pronounce the model's name? Watch a Youtube tutorial

    80B2K ctx Custom licence
    9.1KJul 2023
    • Same category
    • Smaller (80B vs 188B)
    vs
  8. google logo

    gemma-4-31B

    google·Vision

    ≈27 GB

    Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.

    32.7B256K ctx Apache 2.0
    43.8KMar 2026gguf
    • Same category
    • Smaller (32.7B vs 188B)
    • Commercial use OK
    vs
  9. LGAI-EXAONE logo

    EXAONE-4.5-33B

    LGAI-EXAONE·Vision

    ≈23 GB

    We introduce EXAONE 4.5, the first open-weight vision language model developed by LG AI Research. Integrating a dedicated visual encoder into the existing EXAONE 4.0 framework, we expand the model's capability toward multimodality.

    34.4B256K ctx exaone
    23.4KApr 2026gguf
    • Same category
    • Smaller (34.4B vs 188B)
    vs
  10. internlm logo

    Intern-S1-Pro

    internlm·Vision

    ≈546 GB

    💻Github Repo • 🤗Model Collections • 📜Technical Report • 💬Online Chat

    917BA22.9B256K ctx Apache 2.0
    11KFeb 2026
    • Same category
    • Larger (917B vs 188B)
    • Commercial use OK
    vs
  11. Qwen logo

    Qwen3.5-9B

    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
    6.4MFeb 2026ollama
    • Same category
    • Smaller (9.7B vs 188B)
    • Commercial use OK
    • Widely used
    vs
  12. allenai logo

    Molmo-72B-0924

    allenai·Vision

    ≈45 GB

    Molmo is a family of open vision-language models developed by the Allen Institute for AI. Molmo models are trained on PixMo, a dataset of 1 million, highly-curated image-text pairs. It has state-of-the-art performance among multimodal models with a similar size while being fully open-source.

    73.3B4K ctx Apache 2.0
    1.3KSept 2024
    • Same category
    • Smaller (73.3B vs 188B)
    • Commercial use OK
    vs
  13. 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
    5.5MFeb 2026ollama
    • Same category
    • Smaller (2.3B vs 188B)
    • Commercial use OK
    • Widely used
    vs
  14. Qwen logo≈22 GB

    In addition to the original formula, we have further enhanced Qwen2.5-VL-32B's mathematical and problem-solving abilities through reinforcement learning.

    33.5B125K ctx Apache 2.0
    360.8KMar 2025ollama
    • Same category
    • Smaller (33.5B vs 188B)
    • Commercial use OK
    vs
  15. Qwen logo

    Qwen3.5-4B

    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
    4.6MFeb 2026ollama
    • Same category
    • Smaller (4.7B vs 188B)
    • Commercial use OK
    • Widely used
    vs
  16. ByteDance-Seed logo

    UI-TARS-72B-SFT

    ByteDance-Seed·Vision

    ≈47 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.

    73.4B32K ctx Apache 2.0
    249Jan 2025gguf
    • Same category
    • Smaller (73.4B vs 188B)
    • Commercial use OK
    vs
  17. Qwen logo

    Qwen3.5-0.8B

    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
    2.7MFeb 2026ollama
    • Same category
    • Smaller (873M vs 188B)
    • Commercial use OK
    • Widely used
    vs
  18. 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
    470.5KOct 2026gguf
    • Same category
    • Smaller (1.6B vs 188B)
    • Commercial use OK
    vs
  19. OpenGVLab logo

    InternVL2_5-78B-MPO

    OpenGVLab·Vision

    ≈49 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.

    78.4B32K ctx Qwen License
    129Dec 2024gguf
    • Same category
    • Smaller (78.4B vs 188B)
    vs
  20. 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
    6.2MOct 2025ollama
    • Same category
    • Smaller (8.8B vs 188B)
    • Commercial use OK
    • Widely used
    vs
  21. google logo

    gemma-4-26B-A4B

    google·Vision

    ≈18 GB

    Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.

    26.5BA4B256K ctx Apache 2.0
    66.6KMar 2026gguf
    • Same category
    • Smaller (26.5B vs 188B)
    • Commercial use OK
    vs
  22. tencent logo

    Hy4-base

    tencent·Vision

    ≈459 GB

    Hy4 is a new-generation Mixture-of-Experts (MoE) flagship model developed by the Tencent Hy Team, supporting text, image, and video understanding. The language backbone comprises 770B total parameters, of which 49B are activated per token.

    771BA50.3B1M ctx tencent-hy-license
    68Nov 2026
    • Same category
    • Larger (771B vs 188B)
    • Newer release
    vs
  23. moonshotai logo

    Kimi-K3

    moonshotai·Vision

    ≈1701 GB

    Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date. It is a 2.8T-parameter model built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with native vision capabilities and a 1-million-token context window.

    2.78T1M ctx kimi-k3
    734.2KJun 2026ollama
    • Same category
    • Larger (2.78T vs 188B)
    vs
  24. microsoft logo

    AesCode-32B

    microsoft·Vision

    ≈22 GB

    AesCode generates information-rich visual artifacts such as slides, posters, and dashboards as HTML/CSS. The output remains structured, editable, and verifiable, but the task poses a distinct challenge: code models cannot see how layout, hierarchy, and color come together on the canvas.

    33.4B256K ctx Apache 2.0
    1.4KSept 2026gguf
    • Same category
    • Smaller (33.4B vs 188B)
    • Commercial use OK
    vs