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 LFM3-Omni-2B

114 open-weight models that do the same job as LFM3-Omni-2B (2.2B 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 LFM3-Omni-2B with the top 3
the original
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
28.3KOct 2026ollama
--vram
any
--gpus
--quant
  1. 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
    6.8KOct 2026ollama
    • Same category
    • Similar size (2.2B vs 2.2B)
    • Newer release
    vs
  2. 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
    18.2KSept 2026ollama
    • Same category
    • Similar size (2B vs 2.2B)
    vs
  3. 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
    2.7MMar 2026ollama
    • Same category
    • Larger (5.1B vs 2.2B)
    • Commercial use OK
    • Widely used
    vs
  4. 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
    • Larger (8B vs 2.2B)
    • Commercial use OK
    • Widely used
    vs
  5. 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
    90.8KMar 2026gguf
    • Same category
    • Larger (5.1B vs 2.2B)
    • Commercial use OK
    vs
  6. deepseek-ai logo

    Janus-1.3B

    deepseek-ai·Omni

    ≈3.2 GB

    Janus 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.

    2.1B16K ctx MIT
    1.3KOct 2024
    • Same category
    • Similar size (2.1B vs 2.2B)
    • Commercial use OK
    vs
  7. 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
    • Similar size (4.1B vs 2.2B)
    vs
  8. deepseek-ai logo

    JanusFlow-1.3B

    deepseek-ai·Omni

    ≈3.2 GB

    We present JanusFlow, a powerful framework that unifies image understanding and generation in a single model. JanusFlow introduces a minimalist architecture that integrates autoregressive language models with rectified flow, a state-of-the-art method in generative modeling.

    2B16K ctx MIT
    757Nov 2024
    • Same category
    • Similar size (2B vs 2.2B)
    • Commercial use OK
    vs
  9. 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
    408.3KMar 2026gguf
    • Same category
    • Larger (8B vs 2.2B)
    • Commercial use OK
    vs
  10. lmms-lab logo

    Aero-1-Audio

    lmms-lab·Omni

    ≈2.1 GB

    Aero-1-Audio is a compact audio model adept at various audio tasks, including speech recognition, audio understanding, and following audio instructions.

    2.4B32K ctx MIT
    176Apr 2025
    • Same category
    • Similar size (2.4B vs 2.2B)
    • Commercial use OK
    vs
  11. 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
    • Larger (5.3B vs 2.2B)
    vs
  12. 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
    • Larger (5.5B vs 2.2B)
    vs
  13. 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
    2.3KAug 2025
    • Same category
    • Similar size (4B vs 2.2B)
    • Commercial use OK
    vs
  14. 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
    2.4KJun 2025gguf
    • Same category
    • Similar size (4B vs 2.2B)
    • Commercial use OK
    vs
  15. 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
    • Larger (5.4B vs 2.2B)
    vs
  16. 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
    • Larger (12B vs 2.2B)
    • Commercial use OK
    • Widely used
    vs
  17. 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
    • Larger (5.2B vs 2.2B)
    • Commercial use OK
    vs
  18. 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
    • Larger (5.1B vs 2.2B)
    • Commercial use OK
    vs
  19. Skywork logo

    Skywork-UniPic-1.5B

    Skywork·Omni

    ≈1.8 GB

    Skywork-UniPic is a unified autoregressive multimodal model with 1.5 billion parameters, capable of handling three key vision-language tasks within a single architecture:

    1.5BMIT
    113Jul 2025
    • Same category
    • Similar size (1.5B vs 2.2B)
    • Commercial use OK
    vs
  20. 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
    175.9KApr 2026gguf
    • Same category
    • Smaller (470M vs 2.2B)
    • Commercial use OK
    vs
  21. 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
    7.7KOct 2026gguf
    • Same category
    • Smaller (587M vs 2.2B)
    vs
  22. 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
    158.6KFeb 2026gguf
    • Same category
    • Larger (9.4B vs 2.2B)
    • Commercial use OK
    vs
  23. 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
    91.9KNov 2025gguf
    • Same category
    • Larger (8.3B vs 2.2B)
    vs
  24. 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
    328.5KApr 2026gguf
    • Same category
    • Smaller (420M vs 2.2B)
    • Commercial use OK
    vs