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. meta-models logo

    Muse-Spark-Open-816B-A42B

    meta-models·Vision

    ≈490 GB

    Authors: Meta Superintelligence Labs Model Release Date: October 2026 License: Muse Model License

    822BA42B1M ctx muse-model-license
    14.4KSept 2026gguf
    • Same category
    • Larger (822B vs 383B)
    vs
  2. stepfun-ai logo

    Step-3.7-Flash

    stepfun-ai·Vision

    ≈131 GB

    Step 3.7 Flash is a 198B-parameter sparse Mixture-of-Experts (MoE) vision-language model that combines a 196B-parameter language backbone with a 1.8B-parameter vision encoder for native image understanding.

    201B256K ctx Apache 2.0
    9.7KMay 2026gguf
    • Same category
    • Similar size (201B vs 383B)
    • Commercial use OK
    vs
  3. MiniMaxAI logo

    MiniMax-VL-01

    MiniMaxAI·Vision

    ≈274 GB

    We are delighted to introduce our MiniMax-VL-01 model. It adopts the "ViT-MLP-LLM" framework, which is a commonly used technique in the field of multimodal large language models.

    456BA48.8B8K ctx Unknown licence
    5KJan 2025
    • Same category
    • Similar size (456B vs 383B)
    vs
  4. moonshotai logo

    Kimi-K2.6

    moonshotai·Vision

    ≈632 GB

    Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.

    1.03TA33.3B256K ctx modified-mit
    202.3KApr 2026ollama
    • Same category
    • Larger (1.03T vs 383B)
    • Commercial use OK
    vs
  5. moonshotai logo

    Kimi-K2.5

    moonshotai·Vision

    ≈632 GB

    Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base.

    1.03TA33.3B256K ctx modified-mit
    394.7KJan 2026gguf
    • Same category
    • Larger (1.03T vs 383B)
    • Commercial use OK
    vs
  6. baidu logo≈253 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:

    424BA47B128K ctx Apache 2.0
    457Jun 2025
    • Same category
    • Similar size (424B vs 383B)
    • Commercial use OK
    vs
  7. Qwen logo

    Qwen3.5-122B-A10B

    Qwen·Vision

    ≈75 GB

    Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.

    125BA10B256K ctx Apache 2.0
    767.6KFeb 2026ollama
    • Same category
    • Smaller (125B vs 383B)
    • Commercial use OK
    vs
  8. baidu logo≈253 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:

    424BA47B128K ctx Apache 2.0
    268Jun 2025
    • Same category
    • Similar size (424B vs 383B)
    • Commercial use OK
    vs
  9. mistralai logo

    Mistral-Large-4-1T-A52B

    mistralai·Vision

    ≈602 GB

    Mistral Large 4 is our largest and most capable model to date: a 1 trillion-parameter natively multimodal Mixture-of-Experts model with 49 billion active parameters per token (52 billion including embeddings and output layers), trained from scratch on 3,800 NVIDIA Grace Blackwell GPUs in Mistral's…

    1TA52B1M ctx Custom licence
    18.7KSept 2026gguf
    • Same category
    • Larger (1T vs 383B)
    vs
  10. The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:

    424BA47B128K ctx Apache 2.0
    243Jun 2025
    • Same category
    • Similar size (424B vs 383B)
    • Commercial use OK
    vs
  11. NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 is the full-precision release of NVIDIA Nemotron 3.5 Super VL, a vision-language model for reasoning, coding, tool use, document understanding, and video understanding.

    124BA12B1M ctx openmdw-1.1
    74.6KOct 2026gguf
    • Same category
    • Smaller (124B vs 383B)
    • Commercial use OK
    vs
  12. meta-llama logo

    Llama-4-Maverick-17B-128E

    meta-llama·Vision

    ≈240 GB

    The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.

    402BA17B256K ctx Llama 4 Community License
    211Apr 2025gguf
    • Same category
    • Similar size (402B vs 383B)
    vs
  13. tencent logo

    Hy4-flash

    tencent·Vision

    ≈134 GB

    Hy4 flash is our most cost-effective Hy model to date, featuring 220B total parameters (including 64B Engram parameters) with just 12B active parameters per token. It natively accepts text and image inputs, generates text, and supports a context window of up to 1M tokens.

    220B1M ctx tencent-hy-license
    159Nov 2026gguf
    • Same category
    • Similar size (220B vs 383B)
    • Newer release
    vs
  14. tencent logo

    Hy4-flash-base

    tencent·Vision

    ≈133 GB

    Hy4 flash is our most cost-effective Hy model to date, featuring 220B total parameters (including 64B Engram parameters) with just 12B active parameters per token. It natively accepts text and image inputs, generates text, and supports a context window of up to 1M tokens.

    219B1M ctx tencent-hy-license
    129Nov 2026
    • Same category
    • Similar size (219B vs 383B)
    • Newer release
    vs
  15. FINAL-Bench logo

    Darwin-180B-RSI-R3

    FINAL-Bench·Vision

    ≈108 GB

    💻 Run it on your own machine: POCKET-Darwin-180B-GGUF, the 4-bit GGUF of R3 (111 GB), runs on a laptop with an 8 GB GPU and 32 GB RAM, CPU only at 18–21 tok/s, a 128 GB mini PC or one DGX Spark. MMLU-Pro is identical to BF16 (87.65%).

    180BA61.6B256K ctx qwen-community-1.0
    980Oct 2026gguf
    • Same category
    • Smaller (180B vs 383B)
    vs
  16. FINAL-Bench logo

    Darwin-180B-RSI

    FINAL-Bench·Vision

    ≈108 GB

    💻 Run it on your own machine — POCKET-Darwin-180B-GGUF: the 4-bit GGUF of R3 (111 GB) runs on a laptop with an 8 GB GPU and 32 GB RAM, CPU only at 18–21 tok/s, a 128 GB mini PC or one DGX Spark — MMLU-Pro identical to BF16 (87.65%).

    180BA61.6B256K ctx qwen-community-1.0
    787Sept 2026gguf
    • Same category
    • Smaller (180B vs 383B)
    vs
  17. internlm logo

    Intern-S1-Pro

    internlm·Vision

    ≈546 GB

    💻Github Repo • 🤗Model Collections • 📜Technical Report • 💬Online Chat

    917BA22.9B256K ctx Apache 2.0
    11KFeb 2026
    • Same category
    • Larger (917B vs 383B)
    • Commercial use OK
    vs
  18. OpenGVLab logo

    InternVL3_5-241B-A28B

    OpenGVLab·Vision

    ≈145 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.

    241BA28B40K ctx Apache 2.0
    567Aug 2025gguf
    • Same category
    • Similar size (241B vs 383B)
    • Commercial use OK
    vs
  19. inclusionAI logo

    Ling-3.0-flash-VL

    inclusionAI·Vision

    ≈80 GB

    We are introducing Ling-3.0-flash-VL, our next-generation native multimodal model. Built upon Ling-3.0-flash, it brings visual information into the complete process of understanding, reasoning, acting, and verification—advancing beyond image and video perception to solving real-world tasks through…

    125BA5.9B128K ctx MIT
    7.2KSept 2026gguf
    • Same category
    • Smaller (125B vs 383B)
    • Commercial use OK
    vs
  20. Looking for a post-trained model? See the BF16 release for customization or the NVFP4 release for optimized deployment.

    124BA12Bopenmdw-1.1
    2.4KOct 2026
    • Same category
    • Smaller (124B vs 383B)
    • Commercial use OK
    vs
  21. Cactus-Compute logo

    mirage

    Cactus-Compute·Vision

    ? GB

    The package downloads and caches the engine and weights on first use. This repository provides mirage.cact, mirage.safetensors and the model config.

    ?BApache 2.0
    39.8KNov 2026
    • Same category
    • Commercial use OK
    • Newer release
    vs
  22. meta-llama logo≈66 GB

    The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.

    109BA18B10M ctx Llama 4 Community License
    109.7KApr 2025gguf
    • Same category
    • Smaller (109B vs 383B)
    vs
  23. zai-org logo

    GLM-4.5V

    zai-org·Vision

    ≈66 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.

    108BA14.3B64K ctx MIT
    15.6KAug 2025gguf
    • Same category
    • Smaller (108B vs 383B)
    • Commercial use OK
    vs
  24. zai-org logo

    GLM-4.6V

    zai-org·Vision

    ≈66 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.

    108BA14.3B128K ctx MIT
    6KDec 2025gguf
    • Same category
    • Smaller (108B vs 383B)
    • Commercial use OK
    vs