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 Mistral-Large-4-1T-A52B

120 open-weight models that do the same job as Mistral-Large-4-1T-A52B (1T 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
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
20.6KSept 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
    1.6KNov 2026gguf
    • Same category
    • Smaller (321B vs 1T)
    • 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
    49KJul 2025
    • Same category
    • Smaller (321B vs 1T)
    • 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
    15KApr 2025gguf
    • Same category
    • Smaller (402B vs 1T)
    vs
  4. 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
    4KAug 2026gguf
    • Same category
    • Smaller (288B vs 1T)
    • Commercial use OK
    vs
  5. Qwen logo≈142 GB

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

    236BA22B256K ctx Apache 2.0
    317.9KSept 2025ollama
    • Same category
    • Smaller (236B vs 1T)
    • Commercial use OK
    vs
  6. 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
    56.3KNov 2026
    • Same category
    • Commercial use OK
    • Newer release
    vs
  7. 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
    • Smaller (456B vs 1T)
    vs
  8. 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
    593Sept 2026gguf
    • Same category
    • Smaller (321B vs 1T)
    • Commercial use OK
    vs
  9. 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
    882Jun 2025
    • Same category
    • Smaller (424B vs 1T)
    • 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
    5.6KNov 2026gguf
    • Same category
    • Smaller (220B vs 1T)
    • 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
    428Jun 2025
    • Same category
    • Smaller (424B vs 1T)
    • 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
    14.7KMay 2026gguf
    • Same category
    • Smaller (219B vs 1T)
    • Commercial use OK
    vs
  13. 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
    450.9KJun 2025
    • Same category
    • Commercial use OK
    vs
  14. 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
    326.3KJun 2025
    • Same category
    • Commercial use OK
    vs
  15. Qwen logo

    Qwen3.8-27B

    Qwen·Vision

    ≈19 GB

    Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date.

    27.8B256K ctx Apache 2.0
    6.3MAug 2026ollama
    • Same category
    • Smaller (27.8B vs 1T)
    • Commercial use OK
    • Widely used
    vs
  16. 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
    245Jun 2025
    • Same category
    • Smaller (424B vs 1T)
    • Commercial use OK
    vs
  17. 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
    • Smaller (424B vs 1T)
    • Commercial use OK
    vs
  18. Qwen logo≈142 GB

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

    236BA22B256K ctx Apache 2.0
    24.5KSept 2025gguf
    • Same category
    • Smaller (236B vs 1T)
    • Commercial use OK
    vs
  19. internlm logo

    Intern-S1

    internlm·Vision

    ≈145 GB

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

    241BA27.8B64K ctx Apache 2.0
    30.9KJul 2025gguf
    • Same category
    • Smaller (241B vs 1T)
    • Commercial use OK
    vs
  20. 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
    10.2KMay 2026gguf
    • Same category
    • Smaller (201B vs 1T)
    • Commercial use OK
    vs
  21. 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
    826Nov 2026
    • Same category
    • Smaller (219B vs 1T)
    • Newer release
    vs
  22. 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
    6MMar 2026ollama
    • Same category
    • Smaller (31.3B vs 1T)
    • Commercial use OK
    • Widely used
    vs
  23. 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
    6.2MFeb 2026ollama
    • Same category
    • Smaller (9.7B vs 1T)
    • Commercial use OK
    • Widely used
    vs
  24. 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
    4.8MMar 2026ollama
    • Same category
    • Smaller (25.8B vs 1T)
    • Commercial use OK
    • Widely used
    vs