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. moonshotai logo

    Kimi-K2.7-Code

    moonshotai·Vision

    ≈632 GB

    Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by…

    1.03TA33.3B256K ctx modified-mit
    322.7KJun 2026ollama
    • Same category
    • Larger (1.03T vs 188B)
    • Commercial use OK
    vs
  2. Cactus-Compute logo

    mirage

    Cactus-Compute·Vision

    ? GB

    The package downloads and caches the engine and weights on first use. This repository provides mirage.cact, mirage.safetensors and the model config.

    ?BApache 2.0
    43.7KNov 2026
    • Same category
    • Commercial use OK
    vs
  3. Qwen logo

    Qwen3.6-27B

    Qwen·Vision

    ≈19 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…

    27.8B256K ctx Apache 2.0
    2.5MApr 2026ollama
    • Same category
    • Smaller (27.8B vs 188B)
    • Commercial use OK
    • Widely used
    vs
  4. meta-models logo

    Muse-Spark-Open-816B-A42B

    meta-models·Vision

    ≈490 GB

    Authors: Meta Superintelligence Labs Model Release Date: October 2026 License: Muse Model License

    822BA42B1M ctx muse-model-license
    14.4KSept 2026gguf
    • Same category
    • Larger (822B vs 188B)
    vs
  5. baidu logo≈253 GB

    The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:

    424BA47B128K ctx Apache 2.0
    933Jun 2025
    • Same category
    • Larger (424B vs 188B)
    • Commercial use OK
    vs
  6. google logo

    gemma-4-26B-A4B-it

    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.

    25.8BA4B256K ctx Apache 2.0
    4.9MMar 2026ollama
    • Same category
    • Smaller (25.8B vs 188B)
    • Commercial use OK
    • Widely used
    vs
  7. MiniMaxAI logo

    MiniMax-VL-01

    MiniMaxAI·Vision

    ≈274 GB

    We are delighted to introduce our MiniMax-VL-01 model. It adopts the "ViT-MLP-LLM" framework, which is a commonly used technique in the field of multimodal large language models.

    456BA48.8B8K ctx Unknown licence
    4.3KJan 2025
    • Same category
    • Larger (456B vs 188B)
    vs
  8. moonshotai logo

    Kimi-K2.6

    moonshotai·Vision

    ≈632 GB

    Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.

    1.03TA33.3B256K ctx modified-mit
    199KApr 2026ollama
    • Same category
    • Larger (1.03T vs 188B)
    • Commercial use OK
    vs
  9. nvidia logo

    NVLM-D-72B

    nvidia·Vision

    ≈50 GB

    This family of models performs vision-language and text-only tasks including optical character recognition, multimodal reasoning, localization, common sense reasoning, world knowledge utilization, and coding.

    79.4B32K ctx CC BY-NC 4.0
    7.3KSept 2024
    • Same category
    • Smaller (79.4B vs 188B)
    vs
  10. Qwen logo≈47 GB

    We're excited to unveil Qwen2-VL, the latest iteration of our Qwen-VL model, representing nearly a year of innovation.

    73.4B32K ctx Qwen License
    16KSept 2024gguf
    • Same category
    • Smaller (73.4B vs 188B)
    vs
  11. moonshotai logo

    Kimi-K2.5

    moonshotai·Vision

    ≈632 GB

    Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base.

    1.03TA33.3B256K ctx modified-mit
    391.3KJan 2026gguf
    • Same category
    • Larger (1.03T vs 188B)
    • Commercial use OK
    vs
  12. Qwen logo

    Qwen3.5-27B

    Qwen·Vision

    ≈19 GB

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

    27.8B256K ctx Apache 2.0
    1.7MFeb 2026ollama
    • Same category
    • Smaller (27.8B vs 188B)
    • Commercial use OK
    • Widely used
    vs
  13. baidu logo≈253 GB

    The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:

    424BA47B128K ctx Apache 2.0
    446Jun 2025
    • Same category
    • Larger (424B vs 188B)
    • Commercial use OK
    vs
  14. meta-models logo

    Muse-Glimmer-30B

    meta-models·Vision

    ≈19 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.

    29.8B128K ctx Apache 2.0
    153.1KAug 2026ollama
    • Same category
    • Smaller (29.8B vs 188B)
    • Commercial use OK
    vs
  15. baidu logo≈253 GB

    The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:

    424BA47B128K ctx Apache 2.0
    256Jun 2025
    • Same category
    • Larger (424B vs 188B)
    • Commercial use OK
    vs
  16. ByteDance-Seed logo

    UI-TARS-72B-DPO

    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
    2.8KJan 2025gguf
    • Same category
    • Smaller (73.4B vs 188B)
    • Commercial use OK
    vs
  17. PaddlePaddle logo

    UVDoc

    PaddlePaddle·Vision

    ? GB

    The main purpose of text image correction is to carry out geometric transformation on the image to correct the document distortion, inclination, perspective deformation and other problems in the image, so that the subsequent text recognition can be more accurate.

    ?BApache 2.0
    454.3KJun 2025
    • Same category
    • Commercial use OK
    vs
  18. mistralai logo

    Mistral-Large-4-1T-A52B

    mistralai·Vision

    ≈602 GB

    Mistral Large 4 is our largest and most capable model to date: a 1 trillion-parameter natively multimodal Mixture-of-Experts model with 49 billion active parameters per token (52 billion including embeddings and output layers), trained from scratch on 3,800 NVIDIA Grace Blackwell GPUs in Mistral's…

    1TA52B1M ctx Custom licence
    19.3KSept 2026gguf
    • Same category
    • Larger (1T vs 188B)
    vs
  19. The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:

    424BA47B128K ctx Apache 2.0
    235Jun 2025
    • Same category
    • Larger (424B vs 188B)
    • Commercial use OK
    vs
  20. google logo≈18 GB

    DiffusionGemma is a generative model built by Google DeepMind. Based on the 26B A4B Mixture-of-Experts (MoE) Gemma 4 architecture, DiffusionGemma generates tokens using discrete diffusion. This open-weights model is multimodal, handling text, image, and video inputs to generate text output.

    25.8BA4B256K ctx Apache 2.0
    598.6KJun 2026gguf
    • Same category
    • Smaller (25.8B vs 188B)
    • Commercial use OK
    vs
  21. PaddlePaddle logo

    PP-LCNet_x1_0_doc_ori

    PaddlePaddle·Vision

    ? GB

    The Document Image Orientation Classification Module is primarily designed to distinguish the orientation of document images and correct them through post-processing.

    ?BApache 2.0
    330.5KJun 2025
    • Same category
    • Commercial use OK
    vs
  22. meta-llama logo

    Llama-4-Maverick-17B-128E

    meta-llama·Vision

    ≈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.

    402BA17B256K ctx Llama 4 Community License
    218Apr 2025gguf
    • Same category
    • Larger (402B vs 188B)
    vs
  23. huihui-ai logo≈19 GB

    This is an uncensored version of Qwen/Qwen3.8-27B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

    27.8B256K ctx Apache 2.0
    149.9KAug 2026gguf
    • Same category
    • Smaller (27.8B vs 188B)
    • Commercial use OK
    vs
  24. baidu logo

    Qianfan-VL-70B

    baidu·Vision

    ≈46 GB

    The models in this series, including the 4B-parameter end-to-end vision-language model, are presented in the paper Qianfan-OCR: A Unified End-to-End Model for Document Intelligence.

    71.8B32K ctx MIT
    320Sept 2025
    • Same category
    • Smaller (71.8B vs 188B)
    • Commercial use OK
    vs