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 Hy4

120 open-weight models that do the same job as Hy4 (774B 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.

Compare Hy4 with the top 3
the original
tencent logo

Hy4

tencent·Vision

≈461 GB

Hy4 is a new-generation Mixture-of-Experts (MoE) flagship model developed by the Tencent Hy Team, supporting text, image, and video understanding. The language backbone comprises 770B total parameters, of which 49B are activated per token.

774BA53.6B1M ctx tencent-hy-license
89Oct 2026gguf
--vram
any
--gpus
--quant
  1. deepseek-ai logo

    DeepSeek-V4.1-Flash

    deepseek-ai·Vision

    ≈454 GB

    We introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens. The model natively processes images and text, and generates text autoregressively.

    763BA188B1M ctx MIT
    1.4MSept 2026gguf
    • Same category
    • Similar size (763B vs 774B)
    • Commercial use OK
    vs
  2. deepseek-ai logo

    DeepSeek-V4.1-Flash-1017

    deepseek-ai·Vision

    ≈454 GB

    DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks.

    763BA188B1M ctx MIT
    505.4KOct 2026gguf
    • Same category
    • Similar size (763B vs 774B)
    • Commercial use OK
    vs
  3. thinkingmachines logo

    Inkling

    thinkingmachines·Vision

    ≈567 GB

    Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages.

    952BA18.1B1M ctx Apache 2.0
    1.3MJul 2026gguf
    • Same category
    • Similar size (952B vs 774B)
    • Commercial use OK
    vs
  4. moonshotai logo

    Kimi-K2.7-Code

    moonshotai·Vision

    ≈632 GB

    Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by…

    1.03TA33.3B256K ctx modified-mit
    324.1KJun 2026ollama
    • Same category
    • Similar size (1.03T vs 774B)
    • Commercial use OK
    vs
  5. 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
    • Similar size (822B vs 774B)
    vs
  6. 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
    198.9KApr 2026ollama
    • Same category
    • Similar size (1.03T vs 774B)
    • Commercial use OK
    vs
  7. 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
    392.9KJan 2026gguf
    • Same category
    • Similar size (1.03T vs 774B)
    • Commercial use OK
    vs
  8. 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
    19.8KSept 2026gguf
    • Same category
    • Similar size (1T vs 774B)
    vs
  9. zai-org logo

    GLM-5.3-Flash

    zai-org·Vision

    ≈213 GB

    👋 Join our WeChat or Discord community. 📖 Check out the GLM-5.3-Flash blog and GLM-5 Technical report . 📍 Use GLM-5.3-Flash API services on Z.ai API Platform.

    321BA18.3B1M ctx MIT
    6.4MAug 2026ollama
    • Same category
    • Smaller (321B vs 774B)
    • Commercial use OK
    • Widely used
    vs
  10. internlm logo

    Intern-S1-Pro

    internlm·Vision

    ≈546 GB

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

    917BA22.9B256K ctx Apache 2.0
    11.3KFeb 2026
    • Same category
    • Similar size (917B vs 774B)
    • Commercial use OK
    vs
  11. Qwen logo

    Qwen3.5-397B-A17B

    Qwen·Vision

    ≈241 GB

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

    403BA17B256K ctx Apache 2.0
    645.4KFeb 2026gguf
    • Same category
    • Similar size (403B vs 774B)
    • Commercial use OK
    vs
  12. MiniMaxAI logo

    MiniMax-M3

    MiniMaxAI·Vision

    ≈255 GB

    MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.

    427B1M ctx minimax-community
    104.6KJun 2026ollama
    • Same category
    • Similar size (427B vs 774B)
    vs
  13. tencent logo

    Hy4-base

    tencent·Vision

    ≈459 GB

    Hy4 is a new-generation Mixture-of-Experts (MoE) flagship model developed by the Tencent Hy Team, supporting text, image, and video understanding. The language backbone comprises 770B total parameters, of which 49B are activated per token.

    771BA50.3B1M ctx tencent-hy-license
    68Nov 2026
    • Same category
    • Similar size (771B vs 774B)
    • Newer release
    vs
  14. 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
    40.6KNov 2026ollama
    • Same category
    • Smaller (383B vs 774B)
    • Commercial use OK
    • Newer release
    vs
  15. thinkingmachines logo

    Inkling-Small

    thinkingmachines·Vision

    ≈159 GB

    Inkling-Small is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages.

    266BA1.7B1M ctx Apache 2.0
    916.1KJul 2026gguf
    • Same category
    • Smaller (266B vs 774B)
    • Commercial use OK
    vs
  16. zai-org logo

    GLM-5.3-Flash-BF16

    zai-org·Vision

    ≈213 GB

    👋 Join our WeChat or Discord community. 📖 Check out the GLM-5.3-Flash blog and GLM-5 Technical report . 📍 Use GLM-5.3-Flash API services on Z.ai API Platform.

    321BA18.3B1M ctx MIT
    21.9KAug 2026gguf
    • Same category
    • Smaller (321B vs 774B)
    • Commercial use OK
    vs
  17. deepseek-ai logo

    DeepSeek-V4-Flash-Vision-Exp

    deepseek-ai·Vision

    ≈182 GB

    We are excited to introduce DeepSeek-V4-Flash-Vision-Exp, our first experimental multimodal model in the DeepSeek-V4 family. It builds on the DeepSeek-V4-Flash architecture by incorporating visual modules and undergoing continued training to unlock visual understanding capabilities.

    305BA15.2B1M ctx MIT
    30.6KAug 2026gguf
    • Same category
    • Smaller (305B vs 774B)
    • Commercial use OK
    vs
  18. Qwen logo

    Qwen3.8-Flash-Next

    Qwen·Vision

    ≈108 GB

    As the frontier of foundation models pushes toward ever-larger parameter counts and ever-longer context windows, the question is no longer just how much we can scale, but how efficiently we can do so.

    180BA61.6B256K ctx qwen-community-1.0
    2.7MAug 2026ollama
    • Same category
    • Smaller (180B vs 774B)
    • Widely used
    vs
  19. moonshotai logo

    Kimi-K3

    moonshotai·Vision

    ≈1701 GB

    Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date. It is a 2.8T-parameter model built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with native vision capabilities and a 1-million-token context window.

    2.78T1M ctx kimi-k3
    734.8KJun 2026ollama
    • Same category
    • Larger (2.78T vs 774B)
    vs
  20. 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
    • Similar size (403B vs 774B)
    • Commercial use OK
    vs
  21. 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
    150KOct 2026ollama
    • Same category
    • Smaller (220B vs 774B)
    vs
  22. 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
    2.8KNov 2026
    • Same category
    • Larger (1.78T vs 774B)
    • Commercial use OK
    • Newer release
    vs
  23. 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
    481Jul 2026
    • Same category
    • Similar size (404B vs 774B)
    • Commercial use OK
    vs
  24. moonshotai logo

    Kimi-K3.1-Pro

    moonshotai·Vision

    ≈1701 GB

    Kimi K3.1 Pro is an open-weight, natively multimodal agentic model, and our most capable 3T-class model to date. Post-trained from Kimi K3 with large-scale joint reinforcement learning across hundreds of downstream domains, it is the first model in the K3.1 series.

    2.78T1M ctx kimi-k3.1-pro
    64.6KNov 2026gguf
    • Same category
    • Larger (2.78T vs 774B)
    • Newer release
    vs