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. OpenGVLab logo

    InternVL3_5-30B-A3B

    OpenGVLab·Vision

    ≈20 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.

    30.8BA3B40K ctx Apache 2.0
    7.9KAug 2025gguf
    • Same category
    • Similar size (30.8B vs 26.4B)
    • Commercial use OK
    vs
  2. bottlecapai logo

    ThinkingCap-Qwen3.6-27B

    bottlecapai·Vision

    ≈19 GB

    Capability of Qwen3.6-27B with 50% less thinking tokens on average, and over 90% less in best cases. Achieved via finetuning Qwen3.6-27B (Qwen Team, 2026) with state-of-the-art algorithms on a curated set of problems of various domains and difficulty.

    27.4B256K ctx Apache 2.0
    203Jul 2026gguf
    • Same category
    • Similar size (27.4B vs 26.4B)
    • Commercial use OK
    vs
  3. tencent logo

    Hy-Embodied-VLM-1.0

    tencent·Vision

    ≈19 GB

    Building capable embodied agents requires not only multimodal perception and understanding, but also agentic capabilities for reasoning about actions, adapting to evolving situations, and interacting with the physical world.

    30.5B32K ctx Apache 2.0
    553Jul 2026
    • Same category
    • Similar size (30.5B vs 26.4B)
    • Commercial use OK
    vs
  4. google logo

    gemma-3-27b-pt

    google·Vision

    ≈21 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.

    27.4BGemma Terms of Use
    7.2KMar 2025gguf
    • Same category
    • Similar size (27.4B vs 26.4B)
    vs
  5. Agnes-AI logo

    Agnes-3.0-Flash

    Agnes-AI·Vision

    ≈22 GB

    This repository contains an earlier open-weight Preview checkpoint of Agnes 3.0 Flash. It is distinct from the newer production/API checkpoint listed on Artificial Analysis. The Preview release has 33B parameters and a context window of 262,144 tokens.

    33.1B256K ctx Apache 2.0
    468Sept 2026gguf
    • Same category
    • Similar size (33.1B vs 26.4B)
    • Commercial use OK
    vs
  6. rhymes-ai logo

    Aria

    rhymes-ai·Vision

    ≈18 GB

    [Dec 1, 2024] We have released the base models (with native multimodal pre-training) for Aria (Aria-Base-8K and Aria-Base-64K) for research purposes and continue training.

    25.3BA4.6B64K ctx Apache 2.0
    18.8KSept 2024
    • Same category
    • Similar size (25.3B vs 26.4B)
    • Commercial use OK
    vs
  7. baidu logo≈19 GB

    Here is an example of how to use the transformers library for inference:

    29.7BA3B128K ctx Apache 2.0
    1.5KNov 2025
    • Same category
    • Similar size (29.7B vs 26.4B)
    • Commercial use OK
    vs
  8. internlm logo

    Intern-S2-Mobius

    internlm·Vision

    ≈22 GB

    We introduce Intern-S2-Mobius, a 35B foundation model built on the Mobius-v0 architecture realized by Xtuner and LMDeploy.

    36B256K ctx Apache 2.0
    1KJul 2026
    • Same category
    • Similar size (36B vs 26.4B)
    • Commercial use OK
    vs
  9. nvidia logo≈22 GB

    NVIDIA-Ising-Calibration-1 analyzes quantum computing calibration experiment plots and generates structured technical text across six analysis question categories. NVIDIA-Ising-Calibration-1 was developed by NVIDIA as a quantum calibration vision-language model built on Qwen3.5-35B-A3B.

    35BA3B256K ctx NVIDIA Open Model License
    2KMar 2026gguf
    • Same category
    • Similar size (35B vs 26.4B)
    • Commercial use OK
    vs
  10. internlm logo

    Intern-S2-Preview

    internlm·Vision

    ≈23 GB

    We introduce Intern-S2-Preview, an efficient 35B scientific multimodal foundation model. Beyond conventional parameter and data scaling, Intern-S2-Preview explores task scaling: increasing the difficulty, diversity, and coverage of scientific tasks to further unlock model capabilities.

    36.1BA4.9B256K ctx Apache 2.0
    1.6KMay 2026
    • Same category
    • Similar size (36.1B vs 26.4B)
    • Commercial use OK
    vs
  11. OpenGVLab logo≈20 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.

    30.8BA3B40K ctx Apache 2.0
    2.2KAug 2025
    • Same category
    • Similar size (30.8B vs 26.4B)
    • Commercial use OK
    vs
  12. 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
    6MOct 2025ollama
    • Same category
    • Smaller (8.8B vs 26.4B)
    • Commercial use OK
    • Widely used
    vs
  13. inclusionAI logo

    UI-Venus-1.5-30B-A3B

    inclusionAI·Vision

    ≈20 GB

    This repository contains the UI-Venus model from the report UI-Venus-1.5 Technical Report. UI-Venus 1.5 is a unified, end-to-end GUI Agent designed for robust real-world applications. The model family includes two dense (2B/8B) and one MoE (30B-A3B) variants to meet various downstream scenarios.

    31.1BA3B256K ctx Apache 2.0
    350Feb 2026gguf
    • Same category
    • Similar size (31.1B vs 26.4B)
    • Commercial use OK
    vs
  14. deepseek-ai logo

    deepseek-vl2

    deepseek-ai·Vision

    ≈19 GB

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

    27.5BDeepSeek License
    2.3KDec 2024
    • Same category
    • Similar size (27.5B vs 26.4B)
    vs
  15. Zyphra logo

    ZAYA1-VL-8B

    Zyphra·Vision

    ≈6.6 GB

    ZAYA1-VL-8B is a vision-language model (VLM) built upon Zyphra's ZAYA1-8B LLM. It has state-of-the-art performance among VLMs for its size and inference efficiency.

    9.7B32K ctx Apache 2.0
    339KApr 2026gguf
    • Same category
    • Smaller (9.7B vs 26.4B)
    • Commercial use OK
    vs
  16. microsoft logo≈11 GB

    Developer: Microsoft Corporation Authorized Representative: Microsoft Ireland Operations Limited, 70 Sir John Rogerson's Quay, Dublin 2, D02 R296, Ireland Release Date: March 4, 2026 License: MIT Parameters: 15B Context Length: 16,384 tokens Inputs: Text and Images Outputs: Text Training GPUs: 240…

    15.1B32K ctx MIT
    9.5KJan 2026gguf
    • Same category
    • Similar size (15.1B vs 26.4B)
    • Commercial use OK
    vs
  17. 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:

    29.4BA3B128K ctx Apache 2.0
    724Jun 2025
    • Same category
    • Similar size (29.4B vs 26.4B)
    • Commercial use OK
    vs
  18. omlab logo

    VLX-Seek-1.5-10B

    omlab·Vision

    ≈7.4 GB

    VLX-Seek-1.5-10B is the open-source 10B model in the VLX-Seek 1.5 family, designed for fine-grained perception and visual grounding in embodied scenarios.

    10B256K ctx Apache 2.0
    82.9KJul 2026gguf
    • Same category
    • Smaller (10B vs 26.4B)
    • Commercial use OK
    vs
  19. moonshotai logo

    Kimi-VL-A3B-Instruct

    moonshotai·Vision

    ≈13 GB

    We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong agent capabilities—all while activating only 2.8B parameters in its language decoder (Kimi-VL-A3B).

    16.4BA3B128K ctx MIT
    31.3KApr 2025gguf
    • Same category
    • Similar size (16.4B vs 26.4B)
    • Commercial use OK
    vs
  20. OpenGVLab logo

    InternVL3_5-38B

    OpenGVLab·Vision

    ≈25 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.

    38.4B40K ctx Apache 2.0
    3.9KAug 2025gguf
    • Same category
    • Similar size (38.4B vs 26.4B)
    • Commercial use OK
    vs
  21. Qwen logo

    Qwen3.5-9B-Base

    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
    266.5KFeb 2026gguf
    • Same category
    • Smaller (9.7B vs 26.4B)
    • Commercial use OK
    vs
  22. 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
    13.4KJun 2025gguf
    • Same category
    • Similar size (16.4B vs 26.4B)
    • Commercial use OK
    vs
    • Same category
    • Similar size (40B vs 26.4B)
    • Commercial use OK
    vs
  23. 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
    405.7KMar 2025ollama
    • Same category
    • Smaller (12.2B vs 26.4B)
    vs