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. microsoft logo

    Fara1.5-27B

    microsoft·Vision

    ≈19 GB

    Fara1.5-27B is a multimodal computer use agent (CUA) for web browsers, from Microsoft Research AI Frontiers. It observes the browser through screenshots and acts on the user's behalf by emitting structured tool calls — click, type, scroll, visit URL, web search, and so on — to complete tasks…

    27.4B256K ctx MIT
    4.3KJul 2026gguf
    • Same category
    • Similar size (27.4B vs 26.4B)
    • Commercial use OK
    vs
  2. Qwen logo≈22 GB

    Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.

    33.4B256K ctx Apache 2.0
    217KOct 2025ollama
    • Same category
    • Similar size (33.4B vs 26.4B)
    • Commercial use OK
    vs
  3. sensenova logo

    SenseNova-6.8-Code2Video

    sensenova·Vision

    ≈19 GB

    We present SenseNova 6.8 Code2Video, a lightweight open model for code-driven video creation. The model builds and renders videos by generating executable code, and currently focuses on short videos implemented entirely in code.

    27.4B256K ctx Apache 2.0
    1.8KOct 2026gguf
    • Same category
    • Similar size (27.4B vs 26.4B)
    • Commercial use OK
    vs
  4. google logo

    gemma-4-31B

    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.

    32.7B256K ctx Apache 2.0
    43.1KMar 2026gguf
    • Same category
    • Similar size (32.7B vs 26.4B)
    • Commercial use OK
    vs
  5. inclusionAI logo

    ZwZ2-27B

    inclusionAI·Vision

    ≈19 GB

    ZwZ2-27B is the Qwen3.6-27B-based model in Zooming-without-Zooming-v2 (ZwZ2). It learns to connect visual evidence across regions through comparison, aggregation, matching, and multi-step reasoning. Training uses full images; inference requires no zooming tools.

    27.4B256K ctx Unknown licence
    1.5KOct 2026gguf
    • Same category
    • Similar size (27.4B vs 26.4B)
    vs
  6. trohrbaugh logo

    Qwen3.8-27B-heretic-ara

    trohrbaugh·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.

    27.4B256K ctx Apache 2.0
    1.2KAug 2026gguf
    • Same category
    • Similar size (27.4B vs 26.4B)
    • Commercial use OK
    vs
  7. LGAI-EXAONE logo

    EXAONE-4.5-33B

    LGAI-EXAONE·Vision

    ≈23 GB

    We introduce EXAONE 4.5, the first open-weight vision language model developed by LG AI Research. Integrating a dedicated visual encoder into the existing EXAONE 4.0 framework, we expand the model's capability toward multimodality.

    34.4B256K ctx exaone
    23.8KApr 2026gguf
    • Same category
    • Similar size (34.4B vs 26.4B)
    vs
    • Same category
    • Similar size (27.8B vs 26.4B)
    • Commercial use OK
    vs
  8. google logo

    medgemma-27b-it

    google·Vision

    ≈21 GB

    This section describes the MedGemma model and how to use it.

    28.8B128K ctx health-ai-developer-foundations
    36.3KJul 2025ollama
    • Same category
    • Similar size (28.8B vs 26.4B)
    vs
  9. Qwen logo≈22 GB

    In addition to the original formula, we have further enhanced Qwen2.5-VL-32B's mathematical and problem-solving abilities through reinforcement learning.

    33.5B125K ctx Apache 2.0
    326.9KMar 2025ollama
    • Same category
    • Similar size (33.5B vs 26.4B)
    • Commercial use OK
    vs
  10. philbert440 logo

    Qwen3.8-27B-Uncensored-Cyber

    philbert440·Vision

    ≈19 GB

    Cyber-specialized de-refusal of Qwen3.8-27B: fully open on the cyber/offensive-security domain while keeping reasoning, factual accuracy, and coherence intact. Vision tower and MTP speculative-decoding head are preserved (full multimodal, image-text-to-text).

    27.4B256K ctx Apache 2.0
    959Aug 2026gguf
    • Same category
    • Similar size (27.4B vs 26.4B)
    • Commercial use OK
    vs
  11. Qwen logo≈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
    42.5KFeb 2026gguf
    • Same category
    • Similar size (36B vs 26.4B)
    • Commercial use OK
    vs
  12. IMPORTANT: NEO and NEO MAX MTP GGUFS, along with complete model card detailing all the reasoning and instruct modes are here:

    27.8B256K ctx Apache 2.0
    573Aug 2026gguf
    • Same category
    • Similar size (27.8B vs 26.4B)
    • Commercial use OK
    vs
  13. tencent logo

    UI-Mate-27B

    tencent·Vision

    ≈19 GB

    Show the workflow once. Let the agent adapt it to the task at hand.

    27.4B256K ctx Apache 2.0
    553Aug 2026gguf
    • Same category
    • Similar size (27.4B vs 26.4B)
    • Commercial use OK
    vs
  14. dealignai logo

    Gemma-4-31B-JANG_4M-CRACK

    dealignai·Vision

    ≈20 GB

    This is an updated version of the original Gemma 4 31B CRACK upload:

    20.2B256K ctx Gemma Terms of Use
    11.5KApr 2026
    • Same category
    • Similar size (20.2B vs 26.4B)
    vs
  15. google logo

    translategemma-27b-it

    google·Vision

    ≈21 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.

    28.8B128K ctx Gemma Terms of Use
    4.4KJan 2026ollama
    • Same category
    • Similar size (28.8B vs 26.4B)
    vs
  16. GrootTeam logo

    Groot-19B-A3B-261023

    GrootTeam·Vision

    ≈13 GB

    Groot is a family of open-weight reasoning models for complex real-world tasks. The models are compact and easy to deploy, strong on reasoning and tool-using workloads, and efficient with token budgets.

    19.4BA3B256K ctx Apache 2.0
    3.3KOct 2026gguf
    • Same category
    • Similar size (19.4B vs 26.4B)
    • Commercial use OK
    vs
  17. tencent logo

    UI-Mate-democua-27B

    tencent·Vision

    ≈19 GB

    Show the workflow once. Let the agent adapt it to the task at hand.

    27.4B256K ctx Apache 2.0
    324Aug 2026gguf
    • Same category
    • Similar size (27.4B vs 26.4B)
    • Commercial use OK
    vs
  18. microsoft logo

    AesCode-32B

    microsoft·Vision

    ≈22 GB

    AesCode generates information-rich visual artifacts such as slides, posters, and dashboards as HTML/CSS. The output remains structured, editable, and verifiable, but the task poses a distinct challenge: code models cannot see how layout, hierarchy, and color come together on the canvas.

    33.4B256K ctx Apache 2.0
    1.4KSept 2026gguf
    • Same category
    • Similar size (33.4B vs 26.4B)
    • Commercial use OK
    vs
  19. h2oai logo

    h2o-lightning-31b

    h2oai·Vision

    ≈21 GB

    H2O-Lightning-31B is a 31B-parameter decision model from H2O.ai, built on google/gemma-4-31B-it. It answers typed decision questions about a record (a document, a ticket, a policy, a conversation), and about images that come with the record. It returns a probability for every option:

    31.3Bh2o-model-non-commercial-licence-v1.1
    642Oct 2026
    • Same category
    • Similar size (31.3B vs 26.4B)
    vs
  20. 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
    12.3KJun 2025
    • Same category
    • Similar size (29.4B vs 26.4B)
    • Commercial use OK
    vs
  21. Qwen logo

    Qwen3.5-9B

    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
    6.3MFeb 2026ollama
    • Same category
    • Smaller (9.7B vs 26.4B)
    • Commercial use OK
    • Widely used
    vs
  22. naver-hyperclovax logo

    HyperCLOVAX-SEED-Think-32B

    naver-hyperclovax·Vision

    ≈23 GB

    HyperCLOVA X SEED 32B Think is an updated vision-language thinking model that advances the SEED Think 14B line beyond simple scaling, pairing a unified vision-language Transformer backbone with a reasoning-centric training recipe.

    33.3B128K ctx hyperclovax
    7.3KDec 2025gguf
    • Same category
    • Similar size (33.3B vs 26.4B)
    vs
  23. Qwen logo≈20 GB

    Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.

    31.1BA3B256K ctx Apache 2.0
    7.1KSept 2025gguf
    • Same category
    • Similar size (31.1B vs 26.4B)
    • Commercial use OK
    vs