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 Inkling-2-Mini

120 open-weight models that do the same job as Inkling-2-Mini (26.4B 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
thinkingmachines logo

Inkling-2-Mini

thinkingmachines·Vision

≈17 GB

Inkling 2 Mini is a general-purpose multimodal model that accepts text and image inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages.

26.4BA3.5B1M ctx Apache 2.0
136Nov 2026ollama
--vram
any
--gpus
--quant
  1. OpenMOSS-Team logo

    MOSS-VL-Realtime

    OpenMOSS-Team·Vision

    ≈8.7 GB

    MOSS-VL is an open vision-language model family from OpenMOSS, supporting image understanding, long-video understanding, and realtime streaming interaction.

    11.3B256K ctx Apache 2.0
    2.3KJul 2026
    • Same category
    • Smaller (11.3B vs 26.4B)
    • Commercial use OK
    vs
  2. KORMo-VL logo

    KORMo-Web-11B

    KORMo-VL·Vision

    ≈8.4 GB

    KORMo-Web-11B is a general-purpose bilingual AI model built on the KORMo foundation model family, developed by KAIST MLP Lab starting from a language model trained entirely from scratch.

    11.2B128K ctx Apache 2.0
    875Nov 2026
    • Same category
    • Smaller (11.2B vs 26.4B)
    • Commercial use OK
    vs
  3. tencent logo

    WeMM-Video-35BA3B

    tencent·Vision

    ≈23 GB

    WeMM-Video-35B-A3B is the mixture-of-experts (35B total, 3B active) checkpoint in the WeMM-Video family. WeMM-Video is a Chinese–English bilingual family for joint audio-visual understanding and reasoning. It accepts text, images, audio, and video and generates text responses.

    36.2BA5B256K ctx Apache 2.0
    5Nov 2026gguf
    • Same category
    • Similar size (36.2B vs 26.4B)
    • Commercial use OK
    vs
  4. 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
    133Nov 2024
    • Same category
    • Similar size (27.7B vs 26.4B)
    vs
  5. CohereLabs logo

    aya-vision-32b

    CohereLabs·Vision

    ≈21 GB

    Cohere Labs Aya Vision 32B is an open weights research release of a 32-billion parameter model with advanced capabilities optimized for a variety of vision-language use cases, including OCR, captioning, visual reasoning, summarization, question answering, code, and more.

    33.1B8K ctx CC BY-NC 4.0
    296Mar 2025
    • Same category
    • Similar size (33.1B vs 26.4B)
    vs
  6. OpenGVLab logo

    InternVL3-14B

    OpenGVLab·Vision

    ≈11 GB

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

    15.1B32K ctx Apache 2.0
    4.4KApr 2025gguf
    • Same category
    • Similar size (15.1B vs 26.4B)
    • Commercial use OK
    vs
  7. ServiceNow-AI logo

    Apriel-1.5-15b-Thinker

    ServiceNow-AI·Vision

    ≈11 GB

    Click here to skip to the technical report -> https://huggingface.co/ServiceNow-AI/Apriel-1.5-15b-Thinker/blob/main/Apriel-1.5-Thinker.pdf

    14.9B262K ctx MIT
    1.4KSept 2025gguf
    • Same category
    • Similar size (14.9B vs 26.4B)
    • Commercial use OK
    vs
  8. 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
    7.1KJul 2026gguf
    • Same category
    • Larger (72B vs 26.4B)
    • Commercial use OK
    vs
  9. zai-org logo≈16 GB

    We launch a new generation of CogVLM2 series of models and open source two models built with Meta-Llama-3-8B-Instruct. Compared with the previous generation of CogVLM open source models, the CogVLM2 series of open source models have the following improvements:

    19.5B8K ctx cogvlm2
    5.4KMay 2024
    • Same category
    • Similar size (19.5B vs 26.4B)
    vs
  10. deepseek-ai logo

    deepseek-vl2-small

    deepseek-ai·Vision

    ≈11 GB

    Introducing DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL.

    16.1BA3.1B4K ctx DeepSeek License
    5.2KDec 2024
    • Same category
    • Similar size (16.1B vs 26.4B)
    vs
  11. 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
    135.3KOct 2025gguf
    • Same category
    • Smaller (8.8B vs 26.4B)
    • Commercial use OK
    vs
  12. ByteDance logo

    UniVR-34B-Planning

    ByteDance·Vision

    ≈23 GB

    UniVR is the first framework that simultaneously learns complex reasoning, fine-grained physical dynamics, and long-term planning from pure visual demonstrations — without relying on dense image-text pairs or task-specific heuristics.

    34BCC BY 4.0
    5Jul 2026
    • Same category
    • Similar size (34B vs 26.4B)
    • Commercial use OK
    vs
  13. moondream logo

    moondream3.1-9B-A2B

    moondream·Vision

    ≈6.5 GB

    Moondream 3.1 is a vision language model with a mixture-of-experts architecture (9B total parameters, 2B active). It delivers state-of-the-art visual reasoning and detection while staying fast and cheap to deploy.

    9.3BA2Bmoondream-model-license-1.0
    8.3KJun 2026
    • Same category
    • Smaller (9.3B vs 26.4B)
    vs
  14. inclusionAI logo

    UI-Venus-2-9B

    inclusionAI·Vision

    ≈6.8 GB

    UI-Venus-2 is a general-purpose foundation GUI agent designed to operate across mobile applications, web platforms, and desktop operating systems through a unified closed-loop reasoning–action framework: the agent observes the current interface, reasons about the task state, executes an action, and…

    9B256K ctx Unknown licence
    6.5KAug 2026gguf
    • Same category
    • Smaller (9B vs 26.4B)
    vs
  15. nvidia logo

    Cosmos-Reason2-8B

    nvidia·Vision

    ≈6.8 GB

    NVIDIA Cosmos Reason 2 is an open, customizable, 8B-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.

    8.8B256K ctx NVIDIA Open Model License
    60KDec 2025gguf
    • Same category
    • Smaller (8.8B vs 26.4B)
    • Commercial use OK
    vs
  16. swiss-ai logo

    Apertus-v1.5-8B

    swiss-ai·Vision

    ≈6.9 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.

    8.9BApache 2.0
    9.3KJul 2026gguf
    • Same category
    • Smaller (8.9B vs 26.4B)
    • Commercial use OK
    vs
  17. allenai logo

    Molmo2-8B

    allenai·Vision

    ≈6.8 GB

    Molmo2 is a family of open vision-language models developed by the Allen Institute for AI (Ai2) that support image, video and multi-image understanding and grounding.

    8.7B36K ctx Apache 2.0
    53.3KDec 2025gguf
    • Same category
    • Smaller (8.7B vs 26.4B)
    • Commercial use OK
    vs
  18. datalab-to logo

    lift

    datalab-to·Vision

    ≈7.2 GB

    lift is a structured extraction model from Datalab that pulls structured JSON out of PDFs and images. Pass any JSON schema and lift returns a JSON object matching it, using schema-constrained decoding to guarantee valid, well-typed output.

    9.7B256K ctx OpenRAIL
    4.6KJun 2026gguf
    • Same category
    • Smaller (9.7B vs 26.4B)
    vs
  19. google logo

    gemma-3-12b-pt

    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.

    12.2BGemma Terms of Use
    21.7KMar 2025gguf
    • Same category
    • Smaller (12.2B vs 26.4B)
    vs
  20. zai-org logo

    GLM-4.1V-9B-Thinking

    zai-org·Vision

    ≈6.9 GB

    📖 View the GLM-4.1V-9B-Thinking paper . 📍 Using GLM-4.1V-9B-Thinking API at Zhipu Foundation Model Open Platform

    10.3B64K ctx MIT
    37.8KJun 2025gguf
    • Same category
    • Smaller (10.3B vs 26.4B)
    • Commercial use OK
    vs
  21. sensenova logo

    SenseNova-Loop-9B

    sensenova·Vision

    ≈7.2 GB

    🔥 2026-11-17: We release SenseNova-Loop-9B, with model weights and code available to the community.

    9.4B512K ctx Apache 2.0
    1.6KNov 2026gguf
    • Same category
    • Smaller (9.4B vs 26.4B)
    • Commercial use OK
    vs
  22. llava-hf logo

    llava-v1.6-34b-hf

    llava-hf·Vision

    ≈22 GB

    The LLaVA-NeXT model was proposed in LLaVA-NeXT: Improved reasoning, OCR, and world knowledge by Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, Yong Jae Lee.

    34.8B4K ctx Unknown licence
    2.5KMar 2024
    • Same category
    • Similar size (34.8B vs 26.4B)
    vs
  23. llm-jp logo

    llm-jp-4-vl-9b

    llm-jp·Vision

    ≈6.9 GB

    Compared with the earlier LLM-jp-4-VL 9B beta, the new model is trained on datasets that have no license or terms-of-use issues for commercial use. It is also enhanced to generate a reasoning trace before a final answer.

    9.1B64K ctx Apache 2.0
    4.2KAug 2026gguf
    • Same category
    • Smaller (9.1B vs 26.4B)
    • Commercial use OK
    vs
  24. FreedomIntelligence logo

    HuatuoGPT-3-9B

    FreedomIntelligence·Vision

    ≈7.1 GB

    HuatuoGPT-3-9B is a medical LLM built on Qwen3.5-9B 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.

    9.4B256K ctx Apache 2.0
    2.1KSept 2026gguf
    • Same category
    • Smaller (9.4B vs 26.4B)
    • Commercial use OK
    vs