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-Small

120 open-weight models that do the same job as Inkling-2-Small (383B 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-Small

thinkingmachines·Vision

≈229 GB

Inkling 2 Small 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.

383B1M ctx Apache 2.0
30.1KNov 2026ollama
--vram
any
--gpus
--quant
  1. google logo

    medgemma-1.5-4b-it

    google·Vision

    ≈4.1 GB

    * License: The use of MedGemma is governed by the Health AI Developer Foundations terms of use. MedGemma has not been evaluated or optimized for multi-turn applications.

    4.3B128K ctx health-ai-developer-foundations
    221.4KJan 2026ollama
    • Same category
    • Smaller (4.3B vs 383B)
    vs
  2. 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
    31.1KSept 2026gguf
    • Same category
    • Smaller (9.4B vs 383B)
    • Commercial use OK
    vs
  3. h2oai logo

    h2o-lightning-4b

    h2oai·Vision

    ≈4.2 GB

    H2O-Lightning-4B is a 4B-parameter decision model from H2O.ai, built on Qwen/Qwen3.5-4B. It answers typed decision questions about a record (a document, a ticket, a policy, a conversation) and about images that come with the record (photos, screenshots, scanned documents, charts).

    4.5B256K ctx Apache 2.0
    26.4KOct 2026gguf
    • Same category
    • Smaller (4.5B vs 383B)
    • Commercial use OK
    vs
  4. 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
    450KSept 2025ollama
    • Same category
    • Smaller (31.1B vs 383B)
    • Commercial use OK
    vs
  5. LiquidAI logo

    d1-3B

    LiquidAI·Vision

    ≈2.8 GB

    d1-3B is a 3B parameter decision model built on LFM2.5-VL-3B. You give it a state (text, JSON, images, or a mix) and a set of questions. It returns calibrated, typed answers in one forward pass with zero output tokens.

    3.1B32K ctx lfm1.0
    21.1KOct 2026gguf
    • Same category
    • Smaller (3.1B vs 383B)
    vs
  6. 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
    17.3KSept 2024gguf
    • Same category
    • Smaller (73.4B vs 383B)
    vs
  7. ibm-granite logo

    granite-vision-4.1-4b

    ibm-granite·Vision

    ≈3.5 GB

    Model Summary: Granite Vision 4.1 4B is a vision-language model (VLM) that delivers frontier-level performance on structured document extraction tasks — chart extraction, table extraction, and semantic key-value pair extraction — in a compact 4B parameter footprint, providing a lightweight…

    4B128K ctx Apache 2.0
    73KApr 2026gguf
    • Same category
    • Smaller (4B vs 383B)
    • Commercial use OK
    vs
  8. 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 383B)
    vs
  9. nvidia logo

    Nemotron-3.5-Parse

    nvidia·Vision

    ≈1.2 GB

    Nemotron 3.5 Parse is a document image parser that produces structured, machine-readable text with semantic layout classes, bounding boxes, and reading order. It combines a C-RADIOv4-SO400M vision encoder with a 10-layer mBART decoder that consumes the visual sequence as a causal prefix.

    631M16K ctx Custom licence
    26.5KSept 2026gguf
    • Same category
    • Smaller (631M vs 383B)
    • Commercial use OK
    vs
  10. tencent logo

    WeVisOne-VL-2B

    tencent·Vision

    ≈2.8 GB

    WeVisOne-VL (WeChat Vision All-in-One) is a unified vision-language model developed by WeChat Vision, Tencent Inc. Built upon Qwen3-VL, it unifies object-level perception (open-vocabulary object detection, referring localization, object counting, object pointing, and OCR) and pixel-level perception…

    2.4B256K ctx Apache 2.0
    17.5KOct 2026gguf
    • Same category
    • Smaller (2.4B vs 383B)
    • Commercial use OK
    vs
  11. LiquidAI logo

    LFM2.5-VL-3B

    LiquidAI·Vision

    ≈2.8 GB

    LFM2.5-VL-3B is a multimodal variant of LFM2.5, a family of hybrid models designed for on-device deployment. It builds on LFM2-VL-3B with further mid- and post-training.

    3.1B32K ctx lfm1.0
    28.7KAug 2026gguf
    • Same category
    • Smaller (3.1B vs 383B)
    vs
  12. LiquidAI logo

    d1-2B

    LiquidAI·Vision

    ≈2.0 GB

    d1-2B is a decision model for text, pictures, and video, built on LFM3-VL-2B. It returns calibrated answers in one forward pass, without generating tokens.

    1.9B125K ctx lfm1.0
    15.5KOct 2026ollama
    • Same category
    • Smaller (1.9B vs 383B)
    vs
  13. Qwen logo≈3.0 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.

    3.8B125K ctx Qwen Research License
    1.9MJan 2025ollama
    • Same category
    • Smaller (3.8B vs 383B)
    • Widely used
    vs
  14. google logo

    gemma-4-26B-A4B

    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.

    26.5BA4B256K ctx Apache 2.0
    68.3KMar 2026gguf
    • Same category
    • Smaller (26.5B vs 383B)
    • Commercial use OK
    vs
  15. 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
    215.6KOct 2025ollama
    • Same category
    • Smaller (33.4B vs 383B)
    • Commercial use OK
    vs
  16. google logo

    gemma-3-4b-it

    google·Vision

    ≈3.7 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.

    4.3B128K ctx Gemma Terms of Use
    991.4KFeb 2025ollama
    • Same category
    • Smaller (4.3B vs 383B)
    vs
  17. LiquidAI logo

    LFM2.5-VL-450M

    LiquidAI·Vision

    ≈1.0 GB

    LFM2.5‑VL-450M is Liquid AI's refreshed version of the first vision-language model, LFM2-VL-450M, built on an updated backbone LFM2.5-350M and tuned for stronger real-world performance. Find more about LFM2.5 family of models in our blog post.

    449M125K ctx lfm1.0
    43.7KApr 2026gguf
    • Same category
    • Smaller (449M vs 383B)
    vs
  18. CohereLabs logo

    North-Micro-Vision-Instruct

    CohereLabs·Vision

    ≈2.9 GB

    North Micro Vision Instruct is a 2.4B-parameter open-weight vision-language model with native-resolution image support, released under the Apache 2.0 license. It is designed as a compact foundation for prototyping, task-specific fine-tuning, and specialized multimodal applications.

    2.5B500K ctx Apache 2.0
    15.7KAug 2026
    • Same category
    • Smaller (2.5B vs 383B)
    • Commercial use OK
    vs
  19. google logo

    medgemma-4b-it

    google·Vision

    ≈4.1 GB

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

    4.3B128K ctx health-ai-developer-foundations
    465.9KMay 2025ollama
    • Same category
    • Smaller (4.3B vs 383B)
    vs
  20. 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
    44KMar 2026gguf
    • Same category
    • Smaller (32.7B vs 383B)
    • Commercial use OK
    vs
  21. nvidia logo≈1.4 GB

    NVIDIA Nemotron Parse v1.1 is designed to understand document semantics and extract text and tables elements with spatial grounding.

    957M9K ctx NVIDIA Open Model License
    113.1KNov 2025
    • Same category
    • Smaller (957M vs 383B)
    • Commercial use OK
    vs
  22. 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
    2.7KJan 2025gguf
    • Same category
    • Smaller (73.4B vs 383B)
    • Commercial use OK
    vs
  23. openbmb logo

    MiniCPM-V-4.6-Thinking

    openbmb·Vision

    ≈1.6 GB

    A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

    1.3B256K ctx Apache 2.0
    26.3KMay 2026gguf
    • Same category
    • Smaller (1.3B vs 383B)
    • Commercial use OK
    vs
  24. 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
    135.1KOct 2025gguf
    • Same category
    • Smaller (8.8B vs 383B)
    • Commercial use OK
    vs