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
2.7KNov 2026
--vram
any
--gpus
--quant
  1. internlm logo

    Intern-S2-397B

    internlm·Vision

    ≈241 GB

    💻Github Repo • 🤗HF Model Collections • 🤖ModelScope Collections • 💬Online Chat

    403BA24.4B256K ctx Apache 2.0
    1.1KSept 2026gguf
    • Same category
    • Smaller (403B vs 1.78T)
    • Commercial use OK
    vs
  2. google logo

    gemma-4-31B-it

    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.

    31.3B256K ctx Apache 2.0
    6.1MMar 2026ollama
    • Same category
    • Smaller (31.3B vs 1.78T)
    • Commercial use OK
    • Widely used
    vs
  3. 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
    6.4MFeb 2026ollama
    • Same category
    • Smaller (9.7B vs 1.78T)
    • Commercial use OK
    • Widely used
    vs
  4. Qwen logo

    Qwen3.5-2B

    Qwen·Vision

    ≈2.2 GB

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

    2.3B256K ctx Apache 2.0
    5.5MFeb 2026ollama
    • Same category
    • Smaller (2.3B vs 1.78T)
    • Commercial use OK
    • Widely used
    vs
  5. Qwen logo

    Qwen3.6-35B-A3B

    Qwen·Vision

    ≈22 GB

    Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding…

    36BA3B256K ctx Apache 2.0
    3.9MApr 2026ollama
    • Same category
    • Smaller (36B vs 1.78T)
    • Commercial use OK
    • Widely used
    vs
  6. google logo

    gemma-4-26B-A4B-it

    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.

    25.8BA4B256K ctx Apache 2.0
    4.9MMar 2026ollama
    • Same category
    • Smaller (25.8B vs 1.78T)
    • Commercial use OK
    • Widely used
    vs
  7. openbmb logo

    MiniCPM-V-4.7-35B-A3B

    openbmb·Vision

    ≈22 GB

    GitHub · On-device results · Evaluation · Examples · Usage · Model weights

    35.2BA3B256K ctx Apache 2.0
    869KOct 2026gguf
    • Same category
    • Smaller (35.2B vs 1.78T)
    • Commercial use OK
    vs
  8. Qwen logo

    Qwen3.5-4B

    Qwen·Vision

    ≈4.3 GB

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

    4.7B256K ctx Apache 2.0
    4.6MFeb 2026ollama
    • Same category
    • Smaller (4.7B vs 1.78T)
    • Commercial use OK
    • Widely used
    vs
  9. MiniMaxAI logo

    MiniMax-M3.1-Flash

    MiniMaxAI·Vision

    ≈132 GB

    MiniMax-M3.1-Flash is a native multimodal mixture-of-experts model for coding, agentic workflows, computer use, and cybersecurity. It supports text, image, and video inputs with a context window of up to 1M tokens.

    220B1M ctx minimax-community
    110.4KOct 2026ollama
    • Same category
    • Smaller (220B vs 1.78T)
    vs
  10. Qwen logo

    Qwen3.6-27B

    Qwen·Vision

    ≈19 GB

    Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding…

    27.8B256K ctx Apache 2.0
    2.5MApr 2026ollama
    • Same category
    • Smaller (27.8B vs 1.78T)
    • Commercial use OK
    • Widely used
    vs
  11. Qwen logo

    Qwen3.5-0.8B

    Qwen·Vision

    ≈1.4 GB

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

    873M256K ctx Apache 2.0
    2.7MFeb 2026ollama
    • Same category
    • Smaller (873M vs 1.78T)
    • Commercial use OK
    • Widely used
    vs
  12. internlm logo

    Intern-S2-Preview-397B

    internlm·Vision

    ≈241 GB

    💻Github Repo • 🤗HF Model Collections • 🤖ModelScope Collections • 💬Online Chat

    404BA25.1B256K ctx Apache 2.0
    487Jul 2026
    • Same category
    • Smaller (404B vs 1.78T)
    • Commercial use OK
    vs
  13. openbmb logo

    MiniCPM-V-4.7-1B

    openbmb·Vision

    ≈1.8 GB

    MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 1B variant. It builds on the family's single-image, multi-image, and video understanding capabilities, combining stronger foundation capabilities with efficient visual encoding and on-device inference.

    1.6B256K ctx Apache 2.0
    470.5KOct 2026gguf
    • Same category
    • Smaller (1.6B vs 1.78T)
    • Commercial use OK
    vs
  14. 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
    6.2MOct 2025ollama
    • Same category
    • Smaller (8.8B vs 1.78T)
    • Commercial use OK
    • Widely used
    vs
  15. stepfun-ai logo

    step3

    stepfun-ai·Vision

    ≈221 GB

    Step3 is our cutting-edge multimodal reasoning model—built on a Mixture-of-Experts architecture with 321B total parameters and 38B active. It is designed end-to-end to minimize decoding costs while delivering top-tier performance in vision–language reasoning.

    321B64K ctx Apache 2.0
    48.6KJul 2025
    • Same category
    • Smaller (321B vs 1.78T)
    • Commercial use OK
    vs
  16. nex-agi logo

    Nex-N2.6

    nex-agi·Vision

    ≈213 GB

    Nex-N2.6 is a multimodal agentic model from Nex-AGI, built on GLM-5.3-Flash. It is designed for computer use, coding, and long-horizon tasks involving tools. This repository contains the FP8-quantized weights of Nex-N2.6, with approximately 321B parameters.

    321BA18.3B1M ctx Apache 2.0
    1.4KNov 2026gguf
    • Same category
    • Smaller (321B vs 1.78T)
    • Commercial use OK
    • Newer release
    vs
  17. meta-llama logo≈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.

    402BA17B1M ctx Llama 4 Community License
    13.9KApr 2025gguf
    • Same category
    • Smaller (402B vs 1.78T)
    vs
  18. Qwen logo

    Qwen3.5-27B

    Qwen·Vision

    ≈19 GB

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

    27.8B256K ctx Apache 2.0
    1.7MFeb 2026ollama
    • Same category
    • Smaller (27.8B vs 1.78T)
    • Commercial use OK
    • Widely used
    vs
  19. nvidia logo≈1.4 GB

    NVIDIA Nemotron Parse 2.0 transforms document images into structured, machine-readable representations with text, layout classes, bounding boxes, and reading-order information.

    903M9K ctx Custom licence
    525.4KJun 2026
    • Same category
    • Smaller (903M vs 1.78T)
    • Commercial use OK
    vs
  20. Qwen logo

    Qwen3.5-35B-A3B

    Qwen·Vision

    ≈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
    1.4MFeb 2026ollama
    • Same category
    • Smaller (36B vs 1.78T)
    • Commercial use OK
    vs
  21. google logo≈18 GB

    DiffusionGemma is a generative model built by Google DeepMind. Based on the 26B A4B Mixture-of-Experts (MoE) Gemma 4 architecture, DiffusionGemma generates tokens using discrete diffusion. This open-weights model is multimodal, handling text, image, and video inputs to generate text output.

    25.8BA4B256K ctx Apache 2.0
    598.6KJun 2026gguf
    • Same category
    • Smaller (25.8B vs 1.78T)
    • Commercial use OK
    vs
  22. Qwen logo≈142 GB

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

    236BA22B256K ctx Apache 2.0
    318KSept 2025ollama
    • Same category
    • Smaller (236B vs 1.78T)
    • Commercial use OK
    vs
  23. dots-studio logo

    dots3-note-prev

    dots-studio·Vision

    ≈206 GB

    dots3-note preview is the first open-weight model in the dots3 family. It is a Mixture-of-Experts model with 280B total parameters, 16B activated parameters, and support for a context length of up to 512K tokens. The model can understand text, images, video, and audio, and produces text outputs.

    288BA25.1B512K ctx Apache 2.0
    4.2KAug 2026gguf
    • Same category
    • Smaller (288B vs 1.78T)
    • Commercial use OK
    vs
  24. Qwen logo≈4.3 GB

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

    4.4B256K ctx Apache 2.0
    3MOct 2025ollama
    • Same category
    • Smaller (4.4B vs 1.78T)
    • Commercial use OK
    • Widely used
    vs