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 InternLumina-U2

114 open-weight models that do the same job as InternLumina-U2 (16B 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
internlm logo

InternLumina-U2

internlm·Omni

≈11 GB

A Multi-Codebook Diffusion Large Language Model for Omni-Visual Understanding, Image Generation and Editing.

16BApache 2.0
0Sept 2026
--vram
any
--gpus
--quant
  1. mistralai logo

    Voxtral-Small-24B-2507

    mistralai·Omni

    ≈16 GB

    Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.

    24.3B128K ctx Apache 2.0
    7.7KJul 2025gguf
    • Same category
    • Similar size (24.3B vs 16B)
    • Commercial use OK
    vs
  2. OpenMOSS-Team logo

    MOSS-Music-8B-Instruct

    OpenMOSS-Team·Omni

    ≈7.0 GB

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

    9.1B40K ctx Apache 2.0
    3.2KApr 2026gguf
    • Same category
    • Similar size (9.1B vs 16B)
    • Commercial use OK
    vs
  3. nvidia logo≈5.8 GB

    Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music

    8.3B128K ctx Custom licence
    4.1KApr 2026
    • Same category
    • Similar size (8.3B vs 16B)
    vs
  4. NVIDIA-NemotronLabs-AI-for-Media-Sports-Tennis is a fine-tuned multimodal large language model derived from Nemotron 3 Nano Omni. It was further trained on an in-house NVIDIA tennis dataset of manually labeled point-level video clips to specialize in tennis match understanding.

    33B256K ctx openmdw-1.1
    2.4KSept 2026gguf
    • Same category
    • Larger (33B vs 16B)
    • Commercial use OK
    vs
  5. inclusionAI logo

    Ming-UniAudio-16B-A3B

    inclusionAI·Omni

    ≈12 GB

    Ming-UniAudio is a novel framework that unifies speech understanding, generation, and editing. Its core is a unified continuous speech tokenizer that effectively unifies semantic and acoustic features within an end-to-end model.

    18.3BA3B32K ctx Apache 2.0
    171Sept 2025
    • Same category
    • Similar size (18.3B vs 16B)
    • Commercial use OK
    vs
  6. OpenMOSS-Team logo

    MOSS-Audio-8B-Instruct

    OpenMOSS-Team·Omni

    ≈7.0 GB

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

    9.1B40K ctx Apache 2.0
    1.7KApr 2026
    • Same category
    • Similar size (9.1B vs 16B)
    • Commercial use OK
    vs
  7. FunAudioLLM logo

    Fun-Audio-Chat-8B

    FunAudioLLM·Omni

    ≈7.2 GB

    Fun-Audio-Chat is a Large Audio Language Model built for natural, low-latency voice interactions. It introduces Dual-Resolution Speech Representations (an efficient 5Hz shared backbone + a 25Hz refined head) to cut compute while keeping high speech quality, and Core-Cocktail training to preserve…

    9.5B256K ctx Apache 2.0
    2.1KDec 2025
    • Same category
    • Similar size (9.5B vs 16B)
    • Commercial use OK
    vs
  8. inclusionAI logo

    Ming-UniVision-16B-A3B

    inclusionAI·Omni

    ≈12 GB

    The public training-content summary identifying Ming-UniVision-16B-A3B is available below. Please refer to the document for its covered model versions, training-content scope, summary version, and update date.

    18.8BA3B32K ctx Apache 2.0
    187Sept 2025
    • Same category
    • Similar size (18.8B vs 16B)
    • Commercial use OK
    vs
  9. OpenMOSS-Team logo

    MOSS-Audio-8B-Thinking

    OpenMOSS-Team·Omni

    ≈7.0 GB

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

    9.1B40K ctx Apache 2.0
    1.3KApr 2026
    • Same category
    • Similar size (9.1B vs 16B)
    • Commercial use OK
    vs
  10. HiDream-ai logo

    HiDream-E1-Full

    HiDream-ai·Omni

    ≈12 GB

    For more features and to experience the full capabilities of our product, please visit https://vivago.ai/.

    17.1BMIT
    218Apr 2025gguf
    • Same category
    • Similar size (17.1B vs 16B)
    • Commercial use OK
    vs
  11. nvidia logo≈5.8 GB

    Music Flamingo (MF) is a fully open, state-of-the-art Large Audio-Language Model (LALM) designed to advance music (including song) understanding in foundational audio models. MF brings together innovations in:

    8.3B32K ctx Custom licence
    5.4KJan 2026gguf
    • Same category
    • Similar size (8.3B vs 16B)
    vs
  12. HiDream-ai logo

    HiDream-E1-1

    HiDream-ai·Omni

    ≈12 GB

    For more features and to experience the full capabilities of our product, please visit https://vivago.ai/.

    17.1BMIT
    119Jul 2025
    • Same category
    • Similar size (17.1B vs 16B)
    • Commercial use OK
    vs
  13. openbmb logo

    MiniCPM-o-2_6

    openbmb·Omni

    ≈6.1 GB

    A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

    8.7B32K ctx Apache 2.0
    38.4KJan 2025gguf
    • Same category
    • Similar size (8.7B vs 16B)
    • Commercial use OK
    vs
  14. NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball is a fine-tuned multimodal large language model derived from Nemotron 3 Nano Omni.

    33B256K ctx openmdw-1.1
    1.1KSept 2026
    • Same category
    • Larger (33B vs 16B)
    • Commercial use OK
    • Newer release
    vs
  15. Qwen logo≈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:

    8.4B8K ctx Apache 2.0
    115KJul 2024gguf
    • Same category
    • Similar size (8.4B vs 16B)
    • Commercial use OK
    vs
  16. google logo

    gemma-4-E2B

    google·Omni

    ≈3.8 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.

    5.1B128K ctx Apache 2.0
    93.3KMar 2026gguf
    • Same category
    • Smaller (5.1B vs 16B)
    • Commercial use OK
    vs
  17. OpenMOSS-Team logo

    MOSS-Music-8B-Thinking

    OpenMOSS-Team·Omni

    ≈7.0 GB

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

    9.1B40K ctx Apache 2.0
    460Apr 2026gguf
    • Same category
    • Similar size (9.1B vs 16B)
    • Commercial use OK
    vs
  18. Since the research community currently lacks a general-purpose audio captioning model, we fine-tuned Qwen3-Omni-30B-A3B to obtain Qwen3-Omni-30B-A3B-Captioner, which produces detailed, low-hallucination captions for arbitrary audio inputs.

    31.7BA3B64K ctx Apache 2.0
    4.3KSept 2025gguf
    • Same category
    • Similar size (31.7B vs 16B)
    • Commercial use OK
    vs
  19. kyutai logo≈6.5 GB

    A speech-to-speech model that reasons before it speaks. GLM-4-Voice-9B trained with reinforcement learning against a binary LLM judge on math word problems — no supervised finetuning stage, the reasoning behaviour is learned from the reward alone.

    9.5B8K ctx glm-4-voice-license
    96Aug 2026
    • Same category
    • Similar size (9.5B vs 16B)
    vs
  20. google logo

    gemma-3n-E4B-it

    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
    8.7KJun 2025ollama
    • Same category
    • Smaller (7.8B vs 16B)
    vs
  21. stepfun-ai logo

    Step-Audio-2-mini

    stepfun-ai·Omni

    ≈5.9 GB

    Step-Audio 2 is an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation, presented in the paper Step-Audio 2 Technical Report.

    8.3B16K ctx Apache 2.0
    2.5KAug 2025
    • Same category
    • Similar size (8.3B vs 16B)
    • Commercial use OK
    vs
  22. nvidia logo≈5.8 GB

    Music Flamingo Think (MF-Think) is the Chain-of-Thought version of the original Music Flamingo, a fully open, state-of-the-art Large Audio-Language Model (LALM) designed to advance music (including song) understanding in foundational audio models. MF brings together innovations in:

    8.3B32K ctx Custom licence
    692Feb 2026
    • Same category
    • Similar size (8.3B vs 16B)
    vs
  23. 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
    • Similar size (8.7B vs 16B)
    • Commercial use OK
    vs
  24. 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
    98.4KApr 2025gguf
    • Same category
    • Smaller (5.5B vs 16B)
    vs