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.

Compare InternLumina-U2 with the top 3
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. google logo

    gemma-4-12B-it

    google·Omni

    ≈11 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.

    12B256K ctx Apache 2.0
    1.6MMay 2026ollama
    • Same category
    • Similar size (12B vs 16B)
    • Commercial use OK
    • Widely used
    vs
  2. google logo

    gemma-4-E4B-it

    google·Omni

    ≈5.9 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.

    8B128K ctx Apache 2.0
    4.3MMar 2026ollama
    • Same category
    • Smaller (8B vs 16B)
    • Commercial use OK
    • Widely used
    vs
  3. google logo

    gemma-4-12B

    google·Omni

    ≈11 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.

    12B256K ctx Apache 2.0
    49.8KMay 2026gguf
    • Same category
    • Similar size (12B vs 16B)
    • Commercial use OK
    vs
  4. sensenova logo

    SenseNova-U1.5-8B-MoT

    sensenova·Omni

    ≈12 GB

    SenseNova-U1.5-8B-MoT is our latest native unified multimodal checkpoint for more accurate, consistent, reliable, and aesthetically compelling visual creation.

    17.5B256K ctx Apache 2.0
    3.7KAug 2026gguf
    • Same category
    • Similar size (17.5B vs 16B)
    • Commercial use OK
    vs
  5. inclusionAI logo

    LLaDA2.0-Uni

    inclusionAI·Omni

    ≈10 GB

    LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

    16.3BA1.5B8K ctx Apache 2.0
    2.2KApr 2026
    • Same category
    • Similar size (16.3B vs 16B)
    • Commercial use OK
    vs
  6. 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
    • Same category
    • Similar size (18.3B vs 16B)
    • Newer release
    vs
  7. openbmb logo

    MiniCPM-o-4_5

    openbmb·Omni

    ≈7.2 GB

    A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Mulitmodal Live Streaming on Your Phone

    9.4B40K ctx Apache 2.0
    155.3KFeb 2026gguf
    • Same category
    • Similar size (9.4B vs 16B)
    • Commercial use OK
    vs
  8. google logo

    gemma-4-E4B

    google·Omni

    ≈5.9 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.

    8B128K ctx Apache 2.0
    438.2KMar 2026gguf
    • Same category
    • Smaller (8B vs 16B)
    • Commercial use OK
    • Widely used
    vs
  9. Qwen logo

    Qwen2.5-Omni-7B

    Qwen·Omni

    ≈7.3 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.

    10.7B32K ctx Apache 2.0
    255.4KMar 2025gguf
    • Same category
    • Similar size (10.7B vs 16B)
    • Commercial use OK
    vs
  10. tencent logo

    WeVisCut

    tencent·Omni

    ≈7.1 GB

    WeVisCut is a 9B tool-using agent that turns knowledge articles or narration scripts into multi-minute edited videos. At each step, it reads the current editing state and selects one of 12 tools for planning, narration, asset retrieval, composition, inspection, or repair.

    9.4B256K ctx Custom licence
    16.7KSept 2026gguf
    • Same category
    • Similar size (9.4B vs 16B)
    • Newer release
    vs
  11. ByteDance-Seed logo

    BAGEL-7B-MoT

    ByteDance-Seed·Omni

    ≈9.7 GB

    We present BAGEL, an open‑source multimodal foundation model with 7B active parameters (14B total) trained on large‑scale interleaved multimodal data.

    14.7B32K ctx Apache 2.0
    8.5KMay 2025gguf
    • Same category
    • Similar size (14.7B vs 16B)
    • Commercial use OK
    vs
  12. KRAFTON logo≈22 GB

    A.X K2 Raon-Speech is a bilingual English/Korean speech language model with approximately 21.2B total parameters and 3.5B active parameters.

    21.2BA3B128K ctx CC BY-NC 4.0
    1.7KJul 2026
    • Same category
    • Similar size (21.2B vs 16B)
    vs
  13. sensenova logo

    SenseNova-U1-8B-MoT

    sensenova·Omni

    ≈12 GB

    - [2026.04.30] Release the preview version of the 8-step inference model SenseNova-U1-8B-MoT-8step-preview. In most cases, the image generation quality of this model closely matches that of the base model (see comparison and existing issues).

    17.6B256K ctx Apache 2.0
    704Apr 2026
    • Same category
    • Similar size (17.6B vs 16B)
    • Commercial use OK
    vs
  14. NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&A, summarization, transcription, and document intelligence workflows.

    33BA3B256K ctx nvidia-open-model-agreement
    96.1KApr 2026gguf
    • Same category
    • Larger (33B vs 16B)
    • Commercial use OK
    vs
  15. google logo

    gemma-4-E2B-it

    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
    2.8MMar 2026ollama
    • Same category
    • Smaller (5.1B vs 16B)
    • Commercial use OK
    • Widely used
    vs
  16. sensenova logo≈12 GB

    SenseNova-U1.5 (Preview) is a natively unified multimodal model built on NEO-unify, featuring new patch encoding and decoding layers.

    17.5B256K ctx Apache 2.0
    158Jul 2026gguf
    • Same category
    • Similar size (17.5B vs 16B)
    • Commercial use OK
    vs
  17. sensenova logo≈12 GB

    - [2026.04.30] Release the preview version of the 8-step inference model SenseNova-U1-8B-MoT-8step-preview. In most cases, the image generation quality of this model closely matches that of the base model (see comparison and existing issues).

    17.6B256K ctx Apache 2.0
    160Jul 2026
    • Same category
    • Similar size (17.6B vs 16B)
    • Commercial use OK
    vs
  18. nvidia logo

    music-flamingo-hf

    nvidia·Omni

    ≈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
    96.9KNov 2025gguf
    • Same category
    • Similar size (8.3B vs 16B)
    vs
  19. Qwen logo≈20 GB

    Qwen3-Omni is the natively end-to-end multilingual omni-modal foundation models. It processes text, images, audio, and video, and delivers real-time streaming responses in both text and natural speech. We introduce several architectural upgrades to improve performance and efficiency. Key features:

    31.7BA3B64K ctx Apache 2.0
    172.6KSept 2025gguf
    • Same category
    • Similar size (31.7B vs 16B)
    • Commercial use OK
    vs
  20. Qwen logo≈22 GB

    Qwen3-Omni is the natively end-to-end multilingual omni-modal foundation models. It processes text, images, audio, and video, and delivers real-time streaming responses in both text and natural speech. We introduce several architectural upgrades to improve performance and efficiency. Key features:

    35.3BA3B64K ctx Apache 2.0
    342.6KSept 2025gguf
    • Same category
    • Larger (35.3B vs 16B)
    • Commercial use OK
    vs
  21. nvidia logo≈5.8 GB

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

    8.3B32K ctx Custom licence
    80.6KOct 2025gguf
    • Same category
    • Similar size (8.3B vs 16B)
    vs
  22. ServiceNow-AI logo

    Apriel-Voice-27B-preview

    ServiceNow-AI·Omni

    ≈19 GB

    An open model for speech, reasoning, and tool use from ServiceNow

    27.2B256K ctx MIT
    1.4KOct 2026
    • Same category
    • Similar size (27.2B vs 16B)
    • Commercial use OK
    • Newer release
    vs
  23. naver-hyperclovax logo

    HyperCLOVAX-SEED-Omni-8B

    naver-hyperclovax·Omni

    ≈8.0 GB

    HyperCLOVA X SEED 8B Omni is a unified multimodal model that brings text, vision, and speech together, based on an auto-regressive Transformer architecture, enabling consistent multimodal understanding and generation.

    10.7B8K ctx hyperclovax
    2.5KDec 2025gguf
    • Same category
    • Similar size (10.7B vs 16B)
    vs
  24. ai-sage logo≈8.1 GB

    GigaChat Audio 10B is an audio-native LLM built on top of the GigaChat 3.1 Lightning text model. A Conformer speech encoder and a modality adapter feed audio embeddings directly into a Mixture-of-Experts decoder, so the model keeps the text quality of its base while adding speech understanding.

    10BA1.8B256K ctx MIT
    897Jul 2026
    • Same category
    • Similar size (10B vs 16B)
    • Commercial use OK
    vs