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 LongCat-2.5

120 open-weight models that do the same job as LongCat-2.5 (1.78T 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
meituan-longcat logo

LongCat-2.5

meituan-longcat·Vision

≈1070 GB

LongCat-2.5 is a native multimodal MoE model for long-horizon agentic tasks, with 1.6 trillion total parameters and approximately 48 billion activated per token.

1.78T512K ctx MIT
2.5KNov 2026
--vram
any
--gpus
--quant
  1. 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 1.78T)
    • Commercial use OK
    vs
  2. NVIDIA Nemotron 3.5 Bolt 74B-A9B is a vision-language model (VLM) designed to run everyday agentic tasks locally. This is the full-precision (BF16) release of this model, intended primarily for customization and post-training rather than direct production inference.

    74.9BA9B256K ctx openmdw-1.1
    8.9KOct 2026gguf
    • Same category
    • Smaller (74.9B vs 1.78T)
    • Commercial use OK
    vs
  3. 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 1.78T)
    • Commercial use OK
    vs
  4. 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 1.78T)
    • Commercial use OK
    vs
  5. 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
    40.4KFeb 2026gguf
    • Same category
    • Smaller (36B vs 1.78T)
    • Commercial use OK
    vs
  6. microsoft logo

    Mage-VL-Cowork

    microsoft·Vision

    ≈4.4 GB

    Mage-VL-Cowork A Full Training Recipe to Learn Hybrid Computer Use from Evolved Harnesses

    4.7B256K ctx Apache 2.0
    5.3KOct 2026gguf
    • Same category
    • Smaller (4.7B vs 1.78T)
    • Commercial use OK
    vs
  7. 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
    60.9KDec 2025gguf
    • Same category
    • Smaller (8.8B vs 1.78T)
    • Commercial use OK
    vs
  8. nvidia logo

    LocateAnything-3B

    nvidia·Vision

    ≈3.0 GB

    LocateAnything is a vision-language model for fast and high-quality visual grounding, enabling precise object localization, dense detection, and point-based localization across diverse domains in both Enterprise Intelligence and Physical AI.

    3.8B32K ctx nvidia-license
    32.3KMar 2026gguf
    • Same category
    • Smaller (3.8B vs 1.78T)
    vs
  9. sensenova logo

    SenseNova-Loop-9B-Preview

    sensenova·Vision

    ≈7.2 GB

    SenseNova-Loop-9B-Preview is a multimodal language model developed for long-context and agentic workflows. It accepts text and images and generates text for applications that combine document understanding, coding, and interaction with external tools.

    9.7B256K ctx Apache 2.0
    5.2KOct 2026gguf
    • Same category
    • Smaller (9.7B vs 1.78T)
    • Commercial use OK
    vs
  10. 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 1.78T)
    • Commercial use OK
    vs
  11. 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
    23.1KApr 2026gguf
    • Same category
    • Smaller (34.4B vs 1.78T)
    vs
  12. orcarouter logo

    Qwen3.8-27B-Uncensored

    orcarouter·Vision

    ≈19 GB

    One Gateway. Every Model. — Route Smarter · Ship Safer · Spend Less.

    27.8BApache 2.0
    8.4KAug 2026gguf
    • Same category
    • Smaller (27.8B vs 1.78T)
    • Commercial use OK
    vs
  13. Qwen logo

    Qwen-Drive-1.0-4B

    Qwen·Vision

    ≈4.0 GB

    Qwen-Drive-1.0 retains the architecture of the pretrained Qwen3.5 vision-language model and integrates 3D perception, visual question answering, and motion planning within a unified framework.

    4.5BApache 2.0
    7.4KAug 2026gguf
    • Same category
    • Smaller (4.5B vs 1.78T)
    • Commercial use OK
    vs
  14. zai-org logo

    GLM-4.6V-Flash

    zai-org·Vision

    ≈6.9 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.

    10.3B128K ctx MIT
    58KDec 2025gguf
    • Same category
    • Smaller (10.3B vs 1.78T)
    • Commercial use OK
    vs
  15. 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
    49.4KDec 2025gguf
    • Same category
    • Smaller (8.7B vs 1.78T)
    • Commercial use OK
    vs
  16. internlm logo

    Intern-Decision-4B

    internlm·Vision

    ≈4.2 GB

    Intern-Decision-4B is a multimodal structured decision model fine-tuned from Qwen3.5-4B. It accepts a shared state, a schema of named questions, and optional images, and returns an answer distribution for every question in one model forward pass.

    4.5B256K ctx Apache 2.0
    5.8KSept 2026gguf
    • Same category
    • Smaller (4.5B vs 1.78T)
    • Commercial use OK
    vs
  17. 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
    • Smaller (402B vs 1.78T)
    vs
  18. 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
    393KMar 2025ollama
    • Same category
    • Smaller (33.5B vs 1.78T)
    • Commercial use OK
    vs
  19. 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
    9.4KJul 2026gguf
    • Same category
    • Smaller (8.9B vs 1.78T)
    • Commercial use OK
    vs
  20. nvidia logo

    Flora-Rewarder

    nvidia·Vision

    ≈19 GB

    Flora-rewarder-27B produces outcome rewards (an episode-level success score), used for monitoring real-world deployments, and process rewards (dense action-quality scores over short time steps), used during reinforcement learning-based post-training.

    27.8B256K ctx NVIDIA Non-Commercial License
    5.5KOct 2026
    • Same category
    • Smaller (27.8B vs 1.78T)
    vs
  21. nvidia logo

    Flora-Captioner

    nvidia·Vision

    ≈19 GB

    Flora-captioner-27B generates one action instruction for a supplied target interval in a robot or human manipulation video. It uses neighboring video context to disambiguate the intended local operation.

    27.4B256K ctx NVIDIA Non-Commercial License
    5.5KOct 2026
    • Same category
    • Smaller (27.4B vs 1.78T)
    vs
  22. 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
    409KMar 2025ollama
    • Same category
    • Smaller (12.2B vs 1.78T)
    vs
  23. OpenGVLab logo

    InternVL3_5-8B

    OpenGVLab·Vision

    ≈6.7 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.

    8.5B40K ctx Apache 2.0
    104.2KAug 2025gguf
    • Same category
    • Smaller (8.5B vs 1.78T)
    • Commercial use OK
    vs
  24. 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
    6.2KAug 2026gguf
    • Same category
    • Smaller (9B vs 1.78T)
    vs