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. stepfun-ai logo

    step3

    stepfun-ai·Vision

    ≈221 GB

    Step3 is our cutting-edge multimodal reasoning model—built on a Mixture-of-Experts architecture with 321B total parameters and 38B active. It is designed end-to-end to minimize decoding costs while delivering top-tier performance in vision–language reasoning.

    321B64K ctx Apache 2.0
    48.6KJul 2025
    • Same category
    • Similar size (321B vs 188B)
    • Commercial use OK
    vs
  2. meta-llama logo≈66 GB

    The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.

    109BA18B10M ctx Llama 4 Community License
    109.8KApr 2025gguf
    • Same category
    • Similar size (109B vs 188B)
    vs
  3. cantina-security logo

    apex-flash-1-abliterated

    cantina-security·Vision

    ≈213 GB

    apex-flash-1-abliterated is an experimental derivative of apex-flash-1, Cantina Security's open-weights security model developed in partnership with Yeta (@yetalabs on X).

    321BA18.3B1M ctx MIT
    707Sept 2026gguf
    • Same category
    • Similar size (321B vs 188B)
    • Commercial use OK
    vs
  4. zai-org logo

    GLM-4.5V

    zai-org·Vision

    ≈66 GB

    This model is part of the GLM-V family of models, introduced in the paper GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.

    108BA14.3B64K ctx MIT
    15.6KAug 2025gguf
    • Same category
    • Similar size (108B vs 188B)
    • Commercial use OK
    vs
  5. zai-org logo

    GLM-4.6V

    zai-org·Vision

    ≈66 GB

    This model is part of the GLM-V family of models, introduced in the paper GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.

    108BA14.3B128K ctx MIT
    6.1KDec 2025gguf
    • Same category
    • Similar size (108B vs 188B)
    • Commercial use OK
    vs
  6. deepseek-ai logo

    DeepSeek-V4.1-Flash

    deepseek-ai·Vision

    ≈454 GB

    We introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens. The model natively processes images and text, and generates text autoregressively.

    763BA188B1M ctx MIT
    1.5MSept 2026gguf
    • Same category
    • Larger (763B vs 188B)
    • Commercial use OK
    vs
  7. CohereLabs logo

    command-a-vision-07-2025

    CohereLabs·Vision

    ≈71 GB

    Cohere Labs Command A Vision is an open weights research release of a 112 billion parameter model optimized for enterprise image understanding tasks, while keeping a low compute footprint.

    112BCC BY-NC 4.0
    9.1KJul 2025
    • Same category
    • Similar size (112B vs 188B)
    vs
  8. OpenGVLab logo

    InternVL3_5-241B-A28B

    OpenGVLab·Vision

    ≈145 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.

    241BA28B40K ctx Apache 2.0
    565Aug 2025gguf
    • Same category
    • Similar size (241B vs 188B)
    • Commercial use OK
    vs
  9. NVIDIA Nemotron 3.5 Bolt 74B-A9B is a vision-language model (VLM) designed to run everyday agentic tasks locally. This is the full-precision (BF16) release of this model, intended primarily for customization and post-training rather than direct production inference.

    74.9BA9B256K ctx openmdw-1.1
    8.7KOct 2026gguf
    • Same category
    • Smaller (74.9B vs 188B)
    • Commercial use OK
    vs
  10. deepseek-ai logo

    DeepSeek-V4.1-Flash-1017

    deepseek-ai·Vision

    ≈454 GB

    DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks.

    763BA188B1M ctx MIT
    502.1KOct 2026gguf
    • Same category
    • Larger (763B vs 188B)
    • Commercial use OK
    vs
  11. internlm logo

    Intern-S2-397B

    internlm·Vision

    ≈241 GB

    💻Github Repo • 🤗HF Model Collections • 🤖ModelScope Collections • 💬Online Chat

    403BA24.4B256K ctx Apache 2.0
    1.1KSept 2026gguf
    • Same category
    • Larger (403B vs 188B)
    • Commercial use OK
    vs
  12. swiss-ai logo

    Apertus-v1.5-70B

    swiss-ai·Vision

    ≈46 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.

    72BApache 2.0
    7.2KJul 2026gguf
    • Same category
    • Smaller (72B vs 188B)
    • Commercial use OK
    vs
  13. Qwen logo

    Qwen3.6-35B-A3B

    Qwen·Vision

    ≈22 GB

    Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding…

    36BA3B256K ctx Apache 2.0
    3.9MApr 2026ollama
    • Same category
    • Smaller (36B vs 188B)
    • Commercial use OK
    • Widely used
    vs
  14. thinkingmachines logo

    Inkling

    thinkingmachines·Vision

    ≈567 GB

    Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages.

    952BA18.1B1M ctx Apache 2.0
    1.4MJul 2026gguf
    • Same category
    • Larger (952B vs 188B)
    • Commercial use OK
    vs
  15. internlm logo

    Intern-S2-Preview-397B

    internlm·Vision

    ≈241 GB

    💻Github Repo • 🤗HF Model Collections • 🤖ModelScope Collections • 💬Online Chat

    404BA25.1B256K ctx Apache 2.0
    487Jul 2026
    • Same category
    • Larger (404B vs 188B)
    • Commercial use OK
    vs
  16. openbmb logo

    MiniCPM-V-4.7-35B-A3B

    openbmb·Vision

    ≈22 GB

    GitHub · On-device results · Evaluation · Examples · Usage · Model weights

    35.2BA3B256K ctx Apache 2.0
    869KOct 2026gguf
    • Same category
    • Smaller (35.2B vs 188B)
    • Commercial use OK
    vs
  17. meta-llama logo≈240 GB

    The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.

    402BA17B1M ctx Llama 4 Community License
    13.9KApr 2025gguf
    • Same category
    • Larger (402B vs 188B)
    vs
  18. deepcogito logo≈66 GB

    The Cogito v2 LLMs are instruction tuned generative models. All models are released under an open license for commercial use.

    109BA18B256K ctx Llama 4 Community License
    740Jul 2025gguf
    • Same category
    • Similar size (109B vs 188B)
    vs
  19. meta-llama logo

    Llama-4-Scout-17B-16E

    meta-llama·Vision

    ≈66 GB

    The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.

    109BA18B256K ctx Llama 4 Community License
    1.8KApr 2025gguf
    • Same category
    • Similar size (109B vs 188B)
    vs
  20. Qwen logo

    Qwen3.8-27B

    Qwen·Vision

    ≈19 GB

    Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date.

    27.8B256K ctx Apache 2.0
    6.6MAug 2026ollama
    • Same category
    • Smaller (27.8B vs 188B)
    • Commercial use OK
    • Widely used
    vs
  21. google logo

    gemma-4-31B-it

    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.

    31.3B256K ctx Apache 2.0
    6.1MMar 2026ollama
    • Same category
    • Smaller (31.3B vs 188B)
    • Commercial use OK
    • Widely used
    vs
  22. Qwen logo≈47 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.

    73.4B125K ctx Qwen License
    54.2KJan 2025ollama
    • Same category
    • Smaller (73.4B vs 188B)
    vs
  23. Qwen logo

    Qwen3.5-35B-A3B

    Qwen·Vision

    ≈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
    1.4MFeb 2026ollama
    • Same category
    • Smaller (36B vs 188B)
    • Commercial use OK
    vs
  24. OpenGVLab logo

    InternVL3-78B

    OpenGVLab·Vision

    ≈49 GB

    We introduce InternVL3, an advanced multimodal large language model (MLLM) series that demonstrates superior overall performance.

    78.4B32K ctx Qwen License
    12.1KApr 2025gguf
    • Same category
    • Smaller (78.4B vs 188B)
    vs