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.

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
27.3KOct 2026ollama
--vram
any
--gpus
--quant
  1. 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
    171Sept 2025
    • Same category
    • Larger (18.3B vs 2.2B)
    • Commercial use OK
    vs
  2. 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
  3. 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
    187Sept 2025
    • Same category
    • Larger (18.8B vs 2.2B)
    • Commercial use OK
    vs
  4. 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
    218Apr 2025gguf
    • Same category
    • Larger (17.1B vs 2.2B)
    • Commercial use OK
    vs
  5. 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
    399Oct 2025
    • Same category
    • Larger (34.1B vs 2.2B)
    • Commercial use OK
    vs
  6. 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
    119Jul 2025
    • Same category
    • Larger (17.1B vs 2.2B)
    • Commercial use OK
    vs
  7. 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
  8. 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
    322Oct 2025
    • Same category
    • Larger (561B vs 2.2B)
    • 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
    178Jan 2024
    • Same category
    • Larger (12B vs 2.2B)
    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 2.2B)
    • 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 2.2B)
    • 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
    267Feb 2025
    • Same category
    • Larger (132B vs 2.2B)
    • 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 2.2B)
    • 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
    148.9KMay 2026gguf
    • Related category
    • Smaller (909M vs 2.2B)
    • 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 2.2B)
    • 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 2.2B)
    • 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 2.2B)
    vs