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 HuatuoGPT-3-27B

120 open-weight models that do the same job as HuatuoGPT-3-27B (27B 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
FreedomIntelligence logo

HuatuoGPT-3-27B

FreedomIntelligence·Vision

≈19 GB

HuatuoGPT-3-27B is a medical LLM built on Qwen3.8-27B with One-stage Policy Optimization (OnePO). OnePO adapts language models to medicine in a single reinforcement-learning stage, without preceding domain-specific supervised fine-tuning.

27B256K ctx Apache 2.0
2.4KSept 2026gguf
--vram
any
--gpus
--quant
  1. moonshotai logo

    Kimi-VL-A3B-Thinking-2506

    moonshotai·Vision

    ≈13 GB

    This is an updated version of Kimi-VL-A3B-Thinking, with following improved abilities:

    16.4BA3B128K ctx MIT
    13KJun 2025gguf
    • Same category
    • Similar size (16.4B vs 27B)
    • Commercial use OK
    vs
  2. baidu logo≈18 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:

    29.4BA3BApache 2.0
    257Jun 2025
    • Same category
    • Similar size (29.4B vs 27B)
    • Commercial use OK
    vs
  3. google logo

    paligemma2-28b-pt-896

    google·Vision

    ≈20 GB

    Transformers PaliGemma 2 28B weights, pre-trained with 896*896 input images and 512 token input/output text sequences. The model is available in the bfloat16 format for fine-tuning.

    27.7BGemma Terms of Use
    775Nov 2024
    • Same category
    • Similar size (27.7B vs 27B)
    vs
  4. google logo

    gemma-3-12b-it

    google·Vision

    ≈11 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.

    12.2B128K ctx Gemma Terms of Use
    405.1KMar 2025ollama
    • Same category
    • Smaller (12.2B vs 27B)
    vs
  5. inclusionAI logo

    LLaDA-UI

    inclusionAI·Vision

    ≈11 GB

    LLaDA-UI is an MoE-based, block-wise diffusion vision-language GUI agent. It understands screenshots at their native aspect ratio and produces grounded coordinates or structured actions for mobile, desktop, and web interfaces.

    16.9BA2.1B8K ctx Unknown licence
    283Sept 2026
    • Same category
    • Similar size (16.9B vs 27B)
    vs
  6. 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
    • Smaller (9.4B vs 27B)
    • Commercial use OK
    vs
  7. 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
    • Smaller (9.4B vs 27B)
    • Commercial use OK
    • Newer release
    vs
  8. 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
    • Smaller (9.4B vs 27B)
    • Commercial use OK
    • Newer release
    vs
  9. Skywork logo

    Skywork-R1V3-38B

    Skywork·Vision

    ≈25 GB

    Skywork-R1V3-38B is the latest and most powerful open-source multimodal reasoning model in the Skywork-R1V series. Built on InternVL-38B, it significantly pushes the boundaries of multimodal and cross-disciplinary intelligence.

    38.4B32K ctx MIT
    1.7KJul 2025gguf
    • Same category
    • Similar size (38.4B vs 27B)
    • Commercial use OK
    vs
  10. meta-llama logo

    Llama-Guard-4-12B

    meta-llama·Vision

    ≈9.1 GB

    Llama Guard 4 is a natively multimodal safety classifier with 12 billion parameters trained jointly on text and multiple images. Llama Guard 4 is a dense architecture pruned from the Llama 4 Scout pre-trained model and fine-tuned for content safety classification.

    12B10M ctx Llama 4 Community License
    192.8KApr 2025gguf
    • Same category
    • Smaller (12B vs 27B)
    vs
  11. OpenGVLab logo

    InternVL3-38B

    OpenGVLab·Vision

    ≈25 GB

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

    38.4B32K ctx Apache 2.0
    3.1KApr 2025
    • Same category
    • Similar size (38.4B vs 27B)
    • Commercial use OK
    vs
  12. moonshotai logo

    Kimi-VL-A3B-Thinking

    moonshotai·Vision

    ≈13 GB

    Please set a higher temperature for thinking model, especially when your problem requires relatively long thinking process. We have updated the following sample script for HF inference.

    16.4BA3B128K ctx MIT
    10.1KApr 2025
    • Same category
    • Similar size (16.4B vs 27B)
    • Commercial use OK
    vs
  13. NVIDIA Nemotron Nano v2 12B VL model enables multi-image reasoning and video understanding, along with strong document intelligence, visual Q&A and summarization capabilities.

    13.2BNVIDIA Open Model License
    16KOct 2025gguf
    • Same category
    • Smaller (13.2B vs 27B)
    • Commercial use OK
    vs
  14. mlfoundations logo

    Gelato-30B-A3B

    mlfoundations·Vision

    ≈20 GB

    We are releasing 🍨 Gelato-30B-A3B, a state-of-the-art grounding model for GUI computer-use tasks! Gelato is trained on our open-sourced Click-100k dataset and achieves 63.88% accuracy on ScreenSpot-Pro and 69.15% / 74.65% on OS-World-G / OS-World-G (Refined), surpassing prior specialized computer…

    31.1BA3B256K ctx Apache 2.0
    78Oct 2025gguf
    • Same category
    • Similar size (31.1B vs 27B)
    • Commercial use OK
    vs
  15. OpenGVLab logo

    InternVL3_5-14B

    OpenGVLab·Vision

    ≈11 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.

    15.1B40K ctx Apache 2.0
    6.4KAug 2025gguf
    • Same category
    • Similar size (15.1B vs 27B)
    • Commercial use OK
    vs
  16. google logo

    translategemma-12b-it

    google·Vision

    ≈11 GB

    TranslateGemma is a family of lightweight, state-of-the-art open translation models from Google, based on the Gemma 3 family of models. TranslateGemma models are designed to handle translation tasks across 55 languages.

    13.2B128K ctx Gemma Terms of Use
    6.2KJan 2026ollama
    • Same category
    • Smaller (13.2B vs 27B)
    vs
  17. Skywork logo

    Skywork-R1V2-38B

    Skywork·Vision

    ≈25 GB

    Skywork-R1V2-38B is a state-of-the-art open-source multimodal reasoning model, achieving top-tier performance across multiple benchmarks: - On MMMU, it scores 73.6%, the highest among all open-source models to date.

    38.4B40K ctx MIT
    1.8KApr 2025
    • Same category
    • Similar size (38.4B vs 27B)
    • Commercial use OK
    vs
  18. ByteDance logo

    Sa2VA-26B

    ByteDance·Vision

    ≈17 GB

    Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels. It achieves comparable performance to SOTA MLLMs Qwen2-VL and InternVL2.5 on question-answering benchmarks.

    25.8B32K ctx Apache 2.0
    163Jan 2025
    • Same category
    • Similar size (25.8B vs 27B)
    • Commercial use OK
    vs
  19. 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
    • Smaller (8.3B vs 27B)
    • Commercial use OK
    • Widely used
    vs
  20. zai-org logo

    GLM-4.6V-Flash

    zai-org·Vision

    ≈6.9 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.

    10.3B128K ctx MIT
    62.7KDec 2025gguf
    • Same category
    • Smaller (10.3B vs 27B)
    • Commercial use OK
    vs
  21. liuhaotian logo

    llava-v1.6-34b

    liuhaotian·Vision

    ≈22 GB

    Model type: LLaVA is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. Base LLM: NousResearch/Nous-Hermes-2-Yi-34B

    34.8B4K ctx Apache 2.0
    15.3KJan 2024ollama
    • Same category
    • Similar size (34.8B vs 27B)
    • Commercial use OK
    vs
  22. 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
    8.1KOct 2026gguf
    • Same category
    • Larger (74.9B vs 27B)
    • Commercial use OK
    • Newer release
    vs
  23. ServiceNow-AI logo

    Apriel-1.6-15b-Thinker

    ServiceNow-AI·Vision

    ≈11 GB

    Apriel-1.6-15B-Thinker is an updated multimodal reasoning model in ServiceNow’s Apriel SLM series, building on Apriel-1.5-15B-Thinker. With significantly improved text and image reasoning capabilities, Apriel-1.6 achieves competitive performance against models up to 10x its size.

    14.9B262K ctx MIT
    1.6KNov 2025gguf
    • Same category
    • Similar size (14.9B vs 27B)
    • Commercial use OK
    vs
  24. google logo≈20 GB

    Transformers PaliGemma 2 28B weights fine-tuned on a mixture of academic tasks using 448x448 input images. PaliGemma 2 mix checkpoints are fine-tuned on a diverse set of tasks and are ready to use out of the box while pt checkpoints are pre-trained and intended for further fine-tuning.

    27.7BGemma Terms of Use
    137Nov 2024
    • Same category
    • Similar size (27.7B vs 27B)
    vs