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
18.2KSept 2026ollama
--vram
any
--gpus
--quant
  1. Tele-AI logo

    TeleStyle

    Tele-AI·Omni

    ? GB

    If you find TeleStyle useful for your research and applications, please cite using this BibTeX:

    ?BApache 2.0
    0Jan 2026
    • Same category
    • Commercial use OK
    vs
  2. BAAI logo

    Emu3.5

    BAAI·Omni

    ≈23 GB

    🔔 Latest: Emu3.5 Web & Mobile Apps and vLLM offline inference are live — see 🔥 News for details.

    34.1B32K ctx Apache 2.0
    391Oct 2025
    • Same category
    • Larger (34.1B vs 2B)
    • Commercial use OK
    vs
  3. zai-org logo

    RealVideo

    zai-org·Omni

    ? GB

    RealVideo is a WebSocket-based video calling system that supports text input. It leverages GLM-4.5-AirX and GLM-TTS models to generate audio responses and utilizes autoregressive diffusion to generate corresponding video frames.

    ?BMIT
    0Dec 2025
    • Same category
    • Commercial use OK
    vs
  4. meituan-longcat logo

    LongCat-Flash-Omni

    meituan-longcat·Omni

    ≈343 GB

    We introduce LongCat-Flash-Omni, a state-of-the-art open-source omni-modal model with 560 billion parameters (with 27B activated), excelling at real-time audio-visual interaction, which is attained by leveraging LongCat-Flash's high-performance Shortcut-connected Mixture-of-Experts (MoE)…

    561B128K ctx MIT
    327Oct 2025
    • Same category
    • Larger (561B vs 2B)
    • 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
    168Sept 2025
    • Same category
    • Larger (18.3B vs 2B)
    • Commercial use OK
    vs
  6. 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
    186Sept 2025
    • Same category
    • Larger (18.8B vs 2B)
    • Commercial use OK
    vs
  7. 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
    228Apr 2025gguf
    • Same category
    • Larger (17.1B vs 2B)
    • Commercial use OK
    vs
  8. 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
    122Jul 2025
    • Same category
    • Larger (17.1B vs 2B)
    • Commercial use OK
    vs
  9. openbmb logo

    OmniLMM-12B

    openbmb·Omni

    ≈8.6 GB

    OmniLMM-12B is the most capable version of OmniLMM currently. The model is built based on EVA02-5B and Zephyr-7B-β, connected with a perceiver resampler layer, and trained on multimodal data in a curriculum fashion. The model has three notable features:

    12B32K ctx Unknown licence
    172Jan 2024
    • Same category
    • Larger (12B vs 2B)
    vs
  10. stepfun-ai logo

    Step-Audio-R1

    stepfun-ai·Omni

    ≈22 GB

    Step-Audio-R1 is the first audio language model to successfully unlock Chain-of-Thought (CoT) reasoning. It decisively solves the "inverted scaling" problem that plagues existing models, where performance degrades with longer reasoning.

    33.5BApache 2.0
    119Nov 2025
    • Same category
    • Larger (33.5B vs 2B)
    • Commercial use OK
    vs
  11. 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
    • Same category
    • Larger (16B vs 2B)
    • Commercial use OK
    vs
  12. stepfun-ai logo

    Step-Audio-Chat

    stepfun-ai·Omni

    ≈112 GB

    This repository contains the Multimodal Large Language Model (LLM) component of Step-Audio. It is a 130 billion parameter multimodal LLM that is responsible for understanding and generating human speech.

    132B32K ctx Apache 2.0
    268Feb 2025
    • Same category
    • Larger (132B vs 2B)
    • Commercial use OK
    vs
  13. Skywork logo≈0.5 GB

    UniPic2-SD3.5M-Kontext-2B is a post-trained T2I model built on the SD3.5-Medium. It focuses on text-to-image generation and image editing, delivering strong quality with a fast generation speed. It runs smoothly on a single 16 GB consumer GPU.

    5MMIT
    69Aug 2025
    • Same category
    • Smaller (5M vs 2B)
    • Commercial use OK
    vs
  14. OpenMOSS-Team logo

    MOSS-Transcribe-Diarize

    OpenMOSS-Team·STT

    ≈2.5 GB

    MOSS-Transcribe-Diarize 0.9B is an end-to-end audio understanding model for long-form multi-speaker transcription, diarization, timestamps, and acoustic event awareness.

    909MApache 2.0
    148KMay 2026gguf
    • Related category
    • Smaller (909M vs 2B)
    • Commercial use OK
    vs
  15. microsoft logo

    VibeVoice-ASR-HF

    microsoft·STT

    ≈10 GB

    VibeVoice-ASR is a unified speech-to-text model designed to handle 60-minute long-form audio in a single pass, generating structured transcriptions containing Who (Speaker), When (Timestamps), and What (Content), with support for Customized Hotwords and over 50 languages.

    8.3BMIT
    16.4KMar 2026gguf
    • Related category
    • Larger (8.3B vs 2B)
    • Commercial use OK
    vs
  16. ACE-Step logo

    acestep-transcriber

    ACE-Step·STT

    ≈13 GB

    ACE-Step Transcriber is the annotation model used by ACE-Step v1.5 for training data labeling. It is a powerful multilingual audio transcription model capable of transcribing both speech and singing voice with high accuracy.

    10.7BMIT
    1.8KJan 2026
    • Related category
    • Larger (10.7B vs 2B)
    • Commercial use OK
    vs
  17. allenai logo

    OLMoASR

    allenai·STT

    ? GB

    OLMoASR is a series of English automatic speech recognition (ASR) models proposed in the OLMoASR: Open Models and Data for Training Robust Speech Recognition Models paper by Huong Ngo et al. from Ai2.

    ?BApache 2.0
    0Jul 2025
    • Related category
    • Commercial use OK
    vs
  18. Menlo logo≈0.6 GB

    Ichigo Whisper is a compact (22M parameters), open-source speech tokenizer for the Whisper-medium model, designed to enhance performance on multilingual with minimal impact on its original English capabilities.

    22MCC BY-NC-SA 4.0
    0Dec 2024
    • Related category
    • Smaller (22M vs 2B)
    vs