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.

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. 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
    1.5KNov 2026gguf
    • Same category
    • Smaller (321B vs 774B)
    • Commercial use OK
    • Newer release
    vs
  2. 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
    48.7KJul 2025
    • Same category
    • Smaller (321B vs 774B)
    • Commercial use OK
    vs
  3. 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
    14.4KApr 2025gguf
    • Same category
    • Similar size (402B vs 774B)
    vs
  4. Qwen logo≈142 GB

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

    236BA22B256K ctx Apache 2.0
    318.9KSept 2025ollama
    • Same category
    • Smaller (236B vs 774B)
    • Commercial use OK
    vs
  5. 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
    4.1KAug 2026gguf
    • Same category
    • Smaller (288B vs 774B)
    • Commercial use OK
    vs
  6. 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
    4.2KJan 2025
    • Same category
    • Similar size (456B vs 774B)
    vs
  7. cantina-security logo

    apex-flash-1-abliterated

    cantina-security·Vision

    ≈213 GB

    apex-flash-1-abliterated is an experimental derivative of apex-flash-1, Cantina Security's open-weights security model developed in partnership with Yeta (@yetalabs on X).

    321BA18.3B1M ctx MIT
    674Sept 2026gguf
    • Same category
    • Smaller (321B vs 774B)
    • 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
    896Jun 2025
    • Same category
    • Similar size (424B vs 774B)
    • Commercial use OK
    vs
  9. Qwen logo≈142 GB

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

    236BA22B256K ctx Apache 2.0
    81.9KSept 2025gguf
    • Same category
    • Smaller (236B vs 774B)
    • Commercial use OK
    vs
  10. 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
    3.9KNov 2026gguf
    • Same category
    • Smaller (220B vs 774B)
    • Newer release
    vs
  11. 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
    430Jun 2025
    • Same category
    • Similar size (424B vs 774B)
    • Commercial use OK
    vs
  12. CohereLabs logo

    command-a-plus-05-2026-bf16

    CohereLabs·Vision

    ≈131 GB

    Command A+ is an open source model with 25 billion active parameters and 218B total parameters model optimized for agentic, multilingual, and reasoning-heavy tasks with a focus on enterprise performance, while also providing support for vision inputs for processing image inputs.

    219BA25.5B200K ctx Apache 2.0
    14.4KMay 2026gguf
    • Same category
    • Smaller (219B vs 774B)
    • Commercial use OK
    vs
  13. 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
    247Jun 2025
    • Same category
    • Similar size (424B vs 774B)
    • Commercial use OK
    vs
  14. 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
    228Jun 2025
    • Same category
    • Similar size (424B vs 774B)
    • Commercial use OK
    vs
  15. 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
    50.7KNov 2026
    • Same category
    • Commercial use OK
    • Newer release
    vs
  16. internlm logo

    Intern-S1

    internlm·Vision

    ≈145 GB

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

    241BA27.8B64K ctx Apache 2.0
    30.5KJul 2025gguf
    • Same category
    • Smaller (241B vs 774B)
    • Commercial use OK
    vs
  17. 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
    9.9KMay 2026gguf
    • Same category
    • Smaller (201B vs 774B)
    • Commercial use OK
    vs
  18. 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
    699Nov 2026
    • Same category
    • Smaller (219B vs 774B)
    • Newer release
    vs
  19. 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
    212Apr 2025gguf
    • Same category
    • Similar size (402B vs 774B)
    vs
  20. 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
    706.9KFeb 2026ollama
    • Same category
    • Smaller (125B vs 774B)
    • Commercial use OK
    vs
  21. 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
    82.2KOct 2026gguf
    • Same category
    • Smaller (124B vs 774B)
    • Commercial use OK
    vs
  22. PaddlePaddle logo

    UVDoc

    PaddlePaddle·Vision

    ? GB

    The main purpose of text image correction is to carry out geometric transformation on the image to correct the document distortion, inclination, perspective deformation and other problems in the image, so that the subsequent text recognition can be more accurate.

    ?BApache 2.0
    453.1KJun 2025
    • Same category
    • Commercial use OK
    vs
  23. PaddlePaddle logo

    PP-LCNet_x1_0_doc_ori

    PaddlePaddle·Vision

    ? GB

    The Document Image Orientation Classification Module is primarily designed to distinguish the orientation of document images and correct them through post-processing.

    ?BApache 2.0
    328.4KJun 2025
    • Same category
    • Commercial use OK
    vs
  24. Agnes-AI logo

    Agnes-2.5-Pro-Theta

    Agnes-AI·Vision

    ≈117 GB

    Agnes 2.5 Pro Theta is a multimodal mixture-of-experts checkpoint distributed with its model implementation, tokenizer, chat template, and image/video processors. This release provides BF16 weights for local inference through Transformers.

    188BApache 2.0
    958Nov 2026
    • Same category
    • Smaller (188B vs 774B)
    • Commercial use OK
    • Newer release
    vs