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 Agnes-2.5-Pro-Theta

120 open-weight models that do the same job as Agnes-2.5-Pro-Theta (188B 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 Agnes-2.5-Pro-Theta with the top 3
the original
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
813Nov 2026
--vram
any
--gpus
--quant
  1. 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
    2.9MAug 2026ollama
    • Same category
    • Similar size (180B vs 188B)
    • Widely used
    vs
  2. 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
    • Similar size (321B vs 188B)
    • Commercial use OK
    • Widely used
    vs
  3. 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
    • Similar size (220B vs 188B)
    vs
  4. 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
    963.2KJul 2026gguf
    • Same category
    • Similar size (266B vs 188B)
    • Commercial use OK
    vs
  5. 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
    737.5KFeb 2026ollama
    • Same category
    • Similar size (125B vs 188B)
    • Commercial use OK
    vs
  6. 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
    • Similar size (236B vs 188B)
    • Commercial use OK
    vs
  7. 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
    84.9KOct 2026gguf
    • Same category
    • Similar size (124B vs 188B)
    • Commercial use OK
    vs
  8. 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
    9.6KMay 2026gguf
    • Same category
    • Similar size (201B vs 188B)
    • Commercial use OK
    vs
  9. 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
    14.3KMay 2026gguf
    • Same category
    • Similar size (219B vs 188B)
    • Commercial use OK
    vs
  10. 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
    1KOct 2026gguf
    • Same category
    • Similar size (180B vs 188B)
    vs
  11. 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
    2.1KNov 2026gguf
    • Same category
    • Similar size (220B vs 188B)
    • Newer release
    vs
  12. Qwen logo≈142 GB

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

    236BA22B256K ctx Apache 2.0
    81.5KSept 2025gguf
    • Same category
    • Similar size (236B vs 188B)
    • Commercial use OK
    vs
  13. 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
    775Sept 2026gguf
    • Same category
    • Similar size (180B vs 188B)
    vs
  14. 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
    30.5KAug 2026gguf
    • Same category
    • Similar size (305B vs 188B)
    • Commercial use OK
    vs
  15. 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
    489Nov 2026
    • Same category
    • Similar size (219B vs 188B)
    • Newer release
    vs
  16. 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
    7.3KSept 2026gguf
    • Same category
    • Similar size (125B vs 188B)
    • Commercial use OK
    vs
  17. 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
    23.6KAug 2026gguf
    • Same category
    • Similar size (321B vs 188B)
    • Commercial use OK
    vs
  18. internlm logo

    Intern-S1

    internlm·Vision

    ≈145 GB

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

    241BA27.8B64K ctx Apache 2.0
    30KJul 2025gguf
    • Same category
    • Similar size (241B vs 188B)
    • Commercial use OK
    vs
  19. 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
    677.3KFeb 2026gguf
    • Same category
    • Larger (403B vs 188B)
    • Commercial use OK
    vs
  20. 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
    37.3KNov 2026ollama
    • Same category
    • Larger (383B vs 188B)
    • Commercial use OK
    vs
  21. Looking for a post-trained model? See the BF16 release for customization or the NVFP4 release for optimized deployment.

    124BA12Bopenmdw-1.1
    2.3KOct 2026
    • Same category
    • Similar size (124B vs 188B)
    • Commercial use OK
    vs
  22. 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
    • Similar size (288B vs 188B)
    • Commercial use OK
    vs
  23. 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
    104.2KJun 2026ollama
    • Same category
    • Larger (427B vs 188B)
    vs
  24. 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
    • Similar size (321B vs 188B)
    • Commercial use OK
    vs