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 Nex-N2.6

120 open-weight models that do the same job as Nex-N2.6 (321B 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
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
--vram
any
--gpus
--quant
  1. zai-org logo

    GLM-4.5V

    zai-org·Vision

    ≈66 GB

    This model is part of the GLM-V family of models, introduced in the paper GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.

    108BA14.3B64K ctx MIT
    15.9KAug 2025gguf
    • Same category
    • Smaller (108B vs 321B)
    • Commercial use OK
    vs
  2. zai-org logo

    GLM-4.6V

    zai-org·Vision

    ≈66 GB

    This model is part of the GLM-V family of models, introduced in the paper GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.

    108BA14.3B128K ctx MIT
    6.1KDec 2025gguf
    • Same category
    • Smaller (108B vs 321B)
    • Commercial use OK
    vs
  3. 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
    vs
  4. CohereLabs logo

    command-a-vision-07-2025

    CohereLabs·Vision

    ≈71 GB

    Cohere Labs Command A Vision is an open weights research release of a 112 billion parameter model optimized for enterprise image understanding tasks, while keeping a low compute footprint.

    112BCC BY-NC 4.0
    10.3KJul 2025
    • Same category
    • Smaller (112B vs 321B)
    vs
  5. NVIDIA Nemotron 3.5 Bolt 74B-A9B is a vision-language model (VLM) designed to run everyday agentic tasks locally. This is the full-precision (BF16) release of this model, intended primarily for customization and post-training rather than direct production inference.

    74.9BA9B256K ctx openmdw-1.1
    8.1KOct 2026gguf
    • Same category
    • Smaller (74.9B vs 321B)
    • Commercial use OK
    vs
  6. swiss-ai logo

    Apertus-v1.5-70B

    swiss-ai·Vision

    ≈46 GB

    Apertus 1.5 is a family of 8B and 70B parameter language models designed to advance the state of multilingual, multimodal, fully open, and transparent AI.

    72BApache 2.0
    7.1KJul 2026gguf
    • Same category
    • Smaller (72B vs 321B)
    • Commercial use OK
    vs
  7. 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
  8. 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
  9. 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 321B)
    • Commercial use OK
    • Widely used
    vs
  10. 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
    3.8MApr 2026ollama
    • Same category
    • Smaller (36B vs 321B)
    • Commercial use OK
    • Widely used
    vs
  11. 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
    875.7KOct 2026gguf
    • Same category
    • Smaller (35.2B vs 321B)
    • Commercial use OK
    vs
  12. deepcogito logo≈66 GB

    The Cogito v2 LLMs are instruction tuned generative models. All models are released under an open license for commercial use.

    109BA18B256K ctx Llama 4 Community License
    710Jul 2025gguf
    • Same category
    • Smaller (109B vs 321B)
    vs
  13. meta-llama logo

    Llama-4-Scout-17B-16E

    meta-llama·Vision

    ≈66 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.

    109BA18B256K ctx Llama 4 Community License
    1.8KApr 2025gguf
    • Same category
    • Smaller (109B vs 321B)
    vs
  14. 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 321B)
    • Commercial use OK
    • Widely used
    vs
  15. 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
    731KJun 2026ollama
    • Same category
    • Larger (2.78T vs 321B)
    vs
  16. 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 321B)
    • Commercial use OK
    • Widely used
    vs
  17. 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 321B)
    • Commercial use OK
    • Widely used
    vs
  18. 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
    5.4MFeb 2026ollama
    • Same category
    • Smaller (2.3B vs 321B)
    • Commercial use OK
    • Widely used
    vs
  19. 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
    2.9KNov 2026
    • Same category
    • Larger (1.78T vs 321B)
    • Commercial use OK
    vs
  20. 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
    4.3MFeb 2026ollama
    • Same category
    • Smaller (4.7B vs 321B)
    • Commercial use OK
    • Widely used
    vs
  21. Qwen logo≈47 GB

    In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models.

    73.4B125K ctx Qwen License
    38.3KJan 2025ollama
    • Same category
    • Smaller (73.4B vs 321B)
    vs
  22. 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
    1.3MFeb 2026ollama
    • Same category
    • Smaller (36B vs 321B)
    • Commercial use OK
    vs
  23. 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
    2.4MApr 2026ollama
    • Same category
    • Smaller (27.8B vs 321B)
    • Commercial use OK
    • Widely used
    vs
  24. OpenGVLab logo

    InternVL3-78B

    OpenGVLab·Vision

    ≈49 GB

    We introduce InternVL3, an advanced multimodal large language model (MLLM) series that demonstrates superior overall performance.

    78.4B32K ctx Qwen License
    11.2KApr 2025gguf
    • Same category
    • Smaller (78.4B vs 321B)
    vs