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 NLD-Uni

114 open-weight models that do the same job as NLD-Uni (18.3B omni), 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
nvidia logo

NLD-Uni

nvidia·Omni

≈12 GB

NLD-Uni is a unified multimodal model for image understanding and image generation. It combines a diffusion language model with specialized visual components and a mixture-of-transformers design.

18.3B128K ctx Unknown licence
1.3KOct 2026
--vram
any
--gpus
--quant
  1. ByteDance-Seed logo

    Tar-7B

    ByteDance-Seed·Omni

    ≈6.1 GB

    Tar-7B is an open-weight omni model with 8.7B parameters from ByteDance-Seed, published on Hugging Face.

    8.7B32K ctx Apache 2.0
    1.7KJul 2025
    • Same category
    • Smaller (8.7B vs 18.3B)
    • Commercial use OK
    vs
  2. Qwen logo

    Qwen2.5-Omni-3B

    Qwen·Omni

    ≈4.1 GB

    Qwen2.5-Omni is an end-to-end multimodal model designed to perceive diverse modalities, including text, images, audio, and video, while simultaneously generating text and natural speech responses in a streaming manner.

    5.5B32K ctx Qwen Research License
    99KApr 2025gguf
    • Same category
    • Smaller (5.5B vs 18.3B)
    vs
  3. sensenova logo≈5.6 GB

    SenseNova-Vision is a unified multimodal model for computer vision. It reformulates heterogeneous visual perception tasks as text generation, image generation, or mixed text-image generation, instead of relying on task-specific heads, decoders, or loss functions for each individual task.

    7BCC BY-NC 4.0
    646Jun 2026
    • Same category
    • Smaller (7B vs 18.3B)
    vs
  4. tencent logo

    Youtu-Parsing-Omni

    tencent·Omni

    ≈4.3 GB

    Youtu-Parsing-Omni is a compact (5B) omni-modal parsing model. Given a single input — a document page, a natural image, a chart / flowchart, a geometry figure, an audio clip or an audio-visual video — it produces one structured JSON envelope that covers both perception (layout elements, text…

    5.3B1M ctx youtu-parsing
    2.4KOct 2026
    • Same category
    • Smaller (5.3B vs 18.3B)
    • Newer release
    vs
  5. deepseek-ai logo

    Janus-Pro-7B

    deepseek-ai·Omni

    ≈5.6 GB

    Janus-Pro is a novel autoregressive framework that unifies multimodal understanding and generation. It addresses the limitations of previous approaches by decoupling visual encoding into separate pathways, while still utilizing a single, unified transformer architecture for processing.

    7B16K ctx MIT
    17.5KJan 2025
    • Same category
    • Smaller (7B vs 18.3B)
    • Commercial use OK
    vs
  6. stepfun-ai logo

    Step-Audio-R1

    stepfun-ai·Omni

    ≈22 GB

    Step-Audio-R1 is the first audio language model to successfully unlock Chain-of-Thought (CoT) reasoning. It decisively solves the "inverted scaling" problem that plagues existing models, where performance degrades with longer reasoning.

    33.5BApache 2.0
    119Nov 2025
    • Same category
    • Similar size (33.5B vs 18.3B)
    • Commercial use OK
    vs
  7. XiaomiMiMo logo

    MiMo-Audio-7B-Instruct

    XiaomiMiMo·Omni

    ≈6.4 GB

    Existing audio language models typically rely on task-specific fine-tuning to accomplish particular audio tasks. In contrast, humans are able to generalize to new audio tasks with only a few examples or simple instructions.

    8B8K ctx MIT
    847Sept 2025
    • Same category
    • Smaller (8B vs 18.3B)
    • Commercial use OK
    vs
  8. XiaomiMiMo logo

    MiMo-Audio-7B-Base

    XiaomiMiMo·Omni

    ≈6.4 GB

    Existing audio language models typically rely on task-specific fine-tuning to accomplish particular audio tasks. In contrast, humans are able to generalize to new audio tasks with only a few examples or simple instructions.

    8B8K ctx MIT
    673Sept 2025
    • Same category
    • Smaller (8B vs 18.3B)
    • Commercial use OK
    vs
  9. google logo

    gemma-3n-E2B-it

    google·Omni

    ≈4.2 GB

    Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3n models are designed for efficient execution on low-resource devices.

    5.4B32K ctx Gemma Terms of Use
    25.9KJun 2025ollama
    • Same category
    • Smaller (5.4B vs 18.3B)
    vs
  10. Qwen logo

    Qwen2-Audio-7B

    Qwen·Omni

    ≈6.5 GB

    Qwen2-Audio is the new series of Qwen large audio-language models. Qwen2-Audio is capable of accepting various audio signal inputs and performing audio analysis or direct textual responses with regard to speech instructions. We introduce two distinct audio interaction modes:

    8.4BApache 2.0
    6.7KJul 2024gguf
    • Same category
    • Smaller (8.4B vs 18.3B)
    • Commercial use OK
    vs
  11. google logo

    gemma-3n-E4B

    google·Omni

    ≈5.7 GB

    Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3n models are designed for efficient execution on low-resource devices.

    7.8B32K ctx Gemma Terms of Use
    737Jun 2025gguf
    • Same category
    • Smaller (7.8B vs 18.3B)
    vs
  12. tencent logo≈4.7 GB

    RxBrain (Hy-Embodied-RxBrain-1.0) is a unified multimodal foundation model for embodied cognition — a single model that couples language reasoning with visual imagination to deliver three core capabilities:

    6.2B256K ctx Apache 2.0
    308Jul 2026
    • Same category
    • Smaller (6.2B vs 18.3B)
    • Commercial use OK
    vs
  13. OpenMOSS-Team logo

    MOSS-Audio-4B-Instruct

    OpenMOSS-Team·Omni

    ≈4.7 GB

    MOSS-Audio is an open-source audio understanding model from MOSI.AI, the OpenMOSS team, and Shanghai Innovation Institute.

    5.2B40K ctx Apache 2.0
    2.3KApr 2026gguf
    • Same category
    • Smaller (5.2B vs 18.3B)
    • Commercial use OK
    vs
  14. aisingapore logo≈3.8 GB

    SEA-LION is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.

    5.1B128K ctx MIT
    1.1KMay 2026gguf
    • Same category
    • Smaller (5.1B vs 18.3B)
    • Commercial use OK
    vs
  15. BAAI logo

    Emu3-Gen

    BAAI·Omni

    ≈6.5 GB

    We introduce Emu3, a new suite of state-of-the-art multimodal models trained solely with next-token prediction ! By tokenizing images, text, and videos into a discrete space, we train a single transformer from scratch on a mixture of multimodal sequences.

    8.5B9K ctx Apache 2.0
    755Sept 2024
    • Same category
    • Smaller (8.5B vs 18.3B)
    • Commercial use OK
    vs
  16. OpenMOSS-Team logo

    MOSS-Audio-4B-Thinking

    OpenMOSS-Team·Omni

    ≈4.7 GB

    MOSS-Audio is an open-source audio understanding model from MOSI.AI, the OpenMOSS team, and Shanghai Innovation Institute.

    5.2B40K ctx Apache 2.0
    674Apr 2026
    • Same category
    • Smaller (5.2B vs 18.3B)
    • Commercial use OK
    vs
  17. openbmb logo

    OmniLMM-12B

    openbmb·Omni

    ≈8.6 GB

    OmniLMM-12B is the most capable version of OmniLMM currently. The model is built based on EVA02-5B and Zephyr-7B-β, connected with a perceiver resampler layer, and trained on multimodal data in a curriculum fashion. The model has three notable features:

    12B32K ctx Unknown licence
    172Jan 2024
    • Same category
    • Similar size (12B vs 18.3B)
    vs
  18. IDEA-Research logo

    Rex-Omni

    IDEA-Research·Omni

    ≈3.2 GB

    This model is Rex-Omni, a 3B-parameter Multimodal Large Language Model (MLLM) presented in the paper "Detect Anything via Next Point Prediction". It is compatible with the Hugging Face transformers library and is licensed under the IDEA License 1.0.

    4.1B125K ctx Custom licence
    14KOct 2025
    • Same category
    • Smaller (4.1B vs 18.3B)
    vs
  19. inclusionAI logo

    Realtime-Venus

    inclusionAI·Omni

    ? GB

    Both directories contain model weights and custom Hugging Face Transformers code. The asynchronous Realtime-Venus-Harness and its external tool integrations live in the GitHub repository.

    ?BApache 2.0
    2.4KSept 2026gguf
    • Same category
    • Commercial use OK
    vs
  20. inclusionAI logo

    Ming-flash-omni-2.0

    inclusionAI·Omni

    ≈63 GB

    The newly released Ming-flash-omni 2.0 leverages the Ling-2.0 architecture—a Mixture-of-Experts (MoE) framework comprising 100B total and 6B active parameters.

    104BA7.5B32K ctx MIT
    31.1KFeb 2026
    • Same category
    • Larger (104B vs 18.3B)
    • Commercial use OK
    vs
  21. FreedomIntelligence logo

    Janus-4o-7B

    FreedomIntelligence·Omni

    ≈5.9 GB

    Janus-4o is a multimodal large language model (MLLM) capable of both text-to-image and text-and-image-to-image generation. It is fine-tuned from Janus-Pro-7B using the ShareGPT-4o-Image dataset to align Janus-Pro with GPT-4o image generation capabilities.

    7.4B16K ctx MIT
    123Jun 2025
    • Same category
    • Smaller (7.4B vs 18.3B)
    • Commercial use OK
    vs
  22. BAAI logo

    Emu3-Stage1

    BAAI·Omni

    ≈6.2 GB

    We introduce Emu3, a new suite of state-of-the-art multimodal models trained solely with next-token prediction ! By tokenizing images, text, and videos into a discrete space, we train a single transformer from scratch on a mixture of multimodal sequences.

    8.5B5K ctx Apache 2.0
    199Oct 2024
    • Same category
    • Smaller (8.5B vs 18.3B)
    • Commercial use OK
    vs
  23. sarvamai logo

    shuka-1

    sarvamai·Omni

    ≈6.7 GB

    Shuka v1 is a language model which natively understands audio in Indic languages. It is an encoder-decoder model built by combining two models: - Our state-of-the-art, in-house, audio encoder: Saaras v1 - Meta’s Llama3-8B-Instruct as the decoder

    8.7BLlama 3 Community License
    238Aug 2024
    • Same category
    • Smaller (8.7B vs 18.3B)
    vs
  24. meituan-longcat logo

    LongCat-Next

    meituan-longcat·Omni

    ≈47 GB

    We develop LongCat-Next, a native multimodal model that processes text, vision, and audio under a single autoregressive objective with minimal inductive bias beyond the language paradigm.

    74.3B128K ctx MIT
    766Mar 2026
    • Same category
    • Larger (74.3B vs 18.3B)
    • Commercial use OK
    vs