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. FlashLabs logo

    Chroma-4B

    FlashLabs·Omni

    ≈4.9 GB

    FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning

    5.9BApache 2.0
    63Nov 2025
    • Same category
    • Smaller (5.9B vs 16B)
    • Commercial use OK
    vs
  2. LiquidAI logo

    LFM3-Omni-2B

    LiquidAI·Omni

    ≈2.2 GB

    LFM3-Omni-2B is Liquid AI's first omni-modal model in the LFM3 family: a single end-to-end model that understands text, images, video and audio, and answers in text and speech. It is built for on-device use: one model replaces a separate ASR model, vision-language model, LLM and TTS model.

    2.2B125K ctx lfm1.0
    24.6KOct 2026ollama
    • Same category
    • Smaller (2.2B vs 16B)
    • Newer release
    vs
  3. NexaAI logo

    OmniNeural-4B

    NexaAI·Omni

    ≈3.6 GB

    OmniNeural is the first fully multimodal model designed specifically for Neural Processing Units (NPUs). It natively understands text, images, and audio, and runs across PCs, mobile devices, automobile, IoT, and robotics.

    4BCC BY 4.0
    2KAug 2025
    • Same category
    • Smaller (4B vs 16B)
    • Commercial use OK
    vs
  4. We have developed and released the family Ichigo-llama3s. This family is natively understanding audio and text input.

    8B128K ctx Apache 2.0
    51Sept 2024gguf
    • Same category
    • Similar size (8B vs 16B)
    • Commercial use OK
    vs
  5. OmniGen2 logo

    OmniGen2

    OmniGen2·Omni

    ≈3.6 GB

    OmniGen2 is a powerful and efficient unified multimodal model. Unlike OmniGen v1, OmniGen2 features two distinct decoding pathways for text and image modalities, utilizing unshared parameters and a decoupled image tokenizer. OmniGen2 has competitive performance across four primary capabilities:

    4BApache 2.0
    2.3KJun 2025gguf
    • Same category
    • Smaller (4B vs 16B)
    • Commercial use OK
    vs
  6. google logo≈1.0 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.

    420M256K ctx Apache 2.0
    349.2KApr 2026gguf
    • Same category
    • Smaller (420M vs 16B)
    • Commercial use OK
    vs
  7. 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
    746Mar 2026
    • Same category
    • Larger (74.3B vs 16B)
    • Commercial use OK
    vs
  8. LiquidAI logo

    d1-Omni-2B

    LiquidAI·Omni

    ≈2.2 GB

    d1-Omni-2B is a decision model for text, pictures, and audio, built on LFM3-Omni-2B. It returns calibrated answers in one forward pass, without generating tokens.

    2.2B125K ctx lfm1.0
    5.9KOct 2026ollama
    • Same category
    • Smaller (2.2B vs 16B)
    • Newer release
    vs
  9. LiquidAI logo

    LFM3-Audio-2B

    LiquidAI·Omni

    ≈2.2 GB

    LFM3-Audio-2B is a compact, fully featured audio model that runs locally on laptops and edge devices. It takes text or audio as input and responds with text, speech, or both.

    2B125K ctx lfm1.0
    16.1KSept 2026ollama
    • Same category
    • Smaller (2B vs 16B)
    • Newer release
    vs
  10. google logo≈1.3 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.

    470M256K ctx Apache 2.0
    181.5KApr 2026gguf
    • Same category
    • Smaller (470M vs 16B)
    • Commercial use OK
    vs
  11. 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
    7.6KFeb 2026
    • Same category
    • Larger (104B vs 16B)
    • Commercial use OK
    vs
  12. OpenMOSS-Team logo

    MOVA-720p

    OpenMOSS-Team·Omni

    ? GB

    We introduce MOVA (MOSS Video and Audio), a foundation model designed to break the "silent era" of open-source video generation. Unlike cascaded pipelines that generate sound as an afterthought, MOVA synthesizes video and audio simultaneously for perfect alignment.

    ?BApache 2.0
    872Jan 2026
    • Same category
    • Commercial use OK
    vs
  13. bytedance-research logo

    Lance

    bytedance-research·Omni

    ? GB

    Lance is a 3B native unified multimodal model that supports image and video understanding, generation, and editing within a single framework.

    ?BApache 2.0
    384May 2026gguf
    • Same category
    • Commercial use OK
    vs
  14. google logo≈1.0 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.

    423M256K ctx Apache 2.0
    39.1KMay 2026gguf
    • Same category
    • Smaller (423M vs 16B)
    • Commercial use OK
    vs
  15. google logo≈0.6 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.

    78M128K ctx Apache 2.0
    39.3KApr 2026gguf
    • Same category
    • Smaller (78M vs 16B)
    • Commercial use OK
    vs
  16. LiquidAI logo

    d1-omni-600M

    LiquidAI·Omni

    ≈1.1 GB

    d1-omni-600M is a 600M parameter decision model built on LFM2.5-Encoder-350M. You give it a state (text or JSON, with images or a voice clip) and a set of named questions.

    587M125K ctx lfm1.0
    9.9KOct 2026gguf
    • Same category
    • Smaller (587M vs 16B)
    • Newer release
    vs
  17. nvidia logo

    audio-flamingo-3

    nvidia·Omni

    ? GB

    Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio-Language Models

    ?BCustom licence
    721Jul 2025
    • Same category
    vs
  18. inclusionAI logo

    Ming-flash-omni-Preview

    inclusionAI·Omni

    ≈63 GB

    Ming-flash-omni Preview, an upgraded version of Ming-Omni, built upon a sparser Mixture-of-Experts (MoE) variant of Ling-Flash-2.0 with 100B total parameters, of which only 6B are active per token.

    104BA7.6B32K ctx MIT
    3KOct 2025
    • Same category
    • Larger (104B vs 16B)
    • Commercial use OK
    vs
  19. google logo≈0.6 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.

    79M128K ctx Apache 2.0
    25KApr 2026gguf
    • Same category
    • Smaller (79M vs 16B)
    • Commercial use OK
    vs
  20. microsoft logo

    OmniParser

    microsoft·Omni

    ? GB

    OmniParser is a general screen parsing tool, which interprets/converts UI screenshot to structured format, to improve existing LLM based UI agent.

    ?BMIT
    1.6KOct 2024
    • Same category
    • Commercial use OK
    vs
  21. adventists-ai logo

    Sophon-Realtime-v1

    adventists-ai·Omni

    ? GB

    An open full-duplex voice model family that hears your tone and speaks with one. Adventists AI · Apache-2.0 · Recommended: Tag · Flash · Try it online · GitHub

    ?BApache 2.0
    0Nov 2026
    • Same category
    • Commercial use OK
    • Newer release
    vs
  22. inclusionAI logo

    Duo-1.0-distill

    inclusionAI·Omni

    ? GB

    Duo is a full-duplex multimodal world model for real-time audio-visual interaction. This repository contains the four-step distilled Realization weights for Duo 1.0.

    ?Bminimax-h3-community-license
    0Nov 2026
    • Same category
    • Newer release
    vs
  23. gpt-omni logo

    mini-omni2

    gpt-omni·Omni

    ? GB

    Mini-Omni2 is an omni-interactive model. It can understand image, audio and text inputs and has end-to-end voice conversations with users. Featuring real-time voice output, omni-capable multimodal understanding and flexible interaction ability with interruption mechanism while speaking.

    ?BMIT
    139Oct 2024gguf
    • Same category
    • Commercial use OK
    vs
  24. fixie-ai logo≈2.9 GB

    Ultravox is a multimodal Speech LLM built around a pretrained Llama3.2-1B-Instruct and whisper-large-v3-turbo backbone.

    683MMIT
    17.9KFeb 2025gguf
    • Same category
    • Smaller (683M vs 16B)
    • Commercial use OK
    vs