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-Audio-2B

114 open-weight models that do the same job as LFM3-Audio-2B (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.

the original
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
17.5KSept 2026ollama
--vram
any
--gpus
--quant
  1. 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
    156.1KFeb 2026gguf
    • Same category
    • Larger (9.4B vs 2B)
    • Commercial use OK
    vs
  2. 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
    657Apr 2026
    • Same category
    • Larger (5.2B vs 2B)
    • Commercial use OK
    vs
  3. nvidia logo≈5.8 GB

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

    8.3B32K ctx Custom licence
    81.4KOct 2025gguf
    • Same category
    • Larger (8.3B vs 2B)
    vs
  4. 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
    • Larger (9.4B vs 2B)
    • Newer release
    vs
  5. 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
    17.7KFeb 2025gguf
    • Same category
    • Smaller (683M vs 2B)
    • 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.

    423M256K ctx Apache 2.0
    36.8KMay 2026gguf
    • Same category
    • Smaller (423M vs 2B)
    • Commercial use OK
    vs
  7. 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
    311Jul 2026
    • Same category
    • Larger (6.2B vs 2B)
    • Commercial use OK
    vs
  8. 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
    627Jun 2026
    • Same category
    • Larger (7B vs 2B)
    vs
  9. 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
    • Larger (8.3B vs 2B)
    vs
  10. 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
    17.8KJan 2025
    • Same category
    • Larger (7B vs 2B)
    • Commercial use OK
    vs
  11. 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
    49.4KMay 2026gguf
    • Same category
    • Larger (12B vs 2B)
    • Commercial use OK
    vs
  12. 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
    • Larger (8.3B vs 2B)
    vs
  13. google logo

    gemma-3n-E2B

    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
    614Jun 2025gguf
    • Same category
    • Larger (5.4B vs 2B)
    vs
  14. We have developed and released the family Ichigo-llama3s. This family is natively understanding audio and text input.

    3.2B128K ctx Apache 2.0
    40Oct 2024gguf
    • Same category
    • Similar size (3.2B vs 2B)
    • Commercial use OK
    vs
  15. 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
    253.4KMar 2025gguf
    • Same category
    • Larger (10.7B vs 2B)
    • Commercial use OK
    vs
  16. 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
    • Larger (9.1B vs 2B)
    • Commercial use OK
    vs
  17. 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
    • Larger (7.8B vs 2B)
    vs
  18. 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
    • Newer release
    vs
  19. 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
    • Larger (8.4B vs 2B)
    • Commercial use OK
    vs
  20. 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
    • Larger (8.7B vs 2B)
    • Commercial use OK
    vs
  21. 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
    • Larger (9.1B vs 2B)
    • Commercial use OK
    vs
  22. 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
    • Larger (9.1B vs 2B)
    • Commercial use OK
    vs
  23. 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
    • Larger (8.3B vs 2B)
    • Commercial use OK
    vs
  24. 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
    • Larger (8.3B vs 2B)
    vs