NEWAgents can now see video via MCP.Try it now →

    AI Model Hub

    Browse AI models for multimodal decomposition and recomposition pipelines — plug any model into your extractors.

    9,002 models available

    Showing 34093432 of 9,002 models

    Any To Any

    unsloth/Qwen2.5-Omni-7B-GGUF

    10K
    69
    transformers
    Text Classification

    ESGBERT/SocRoBERTa-social

    10K
    transformers
    Sentence Similarity

    BAAI/bge-code-v1

    10K
    51
    sentence-transformers
    Automatic Speech Recognition

    eddiegulay/wav2vec2-large-xlsr-mvc-swahili

    10K
    3
    transformers
    Table Question Answering

    google/tapas-base-finetuned-wtq

    10K
    234
    transformers
    Image To Text

    alephpi/FormulaNet

    10K
    2
    Sentence Similarity

    sdadas/mmlw-roberta-base

    10K
    3
    sentence-transformers
    Automatic Speech Recognition

    UsefulSensors/moonshine-base

    10K
    42
    transformers
    Image Classification

    timm/convnext_pico.d1_in1k

    10K
    timm
    Image Segmentation

    openmmlab/upernet-swin-large

    10K
    1
    transformers
    Image Classification

    akashmaggon/vit-base-age-classification

    10K
    1
    transformers
    Image To Image

    prs-eth/marigold-normals-v1-1

    10K
    7
    diffusers
    Image Feature Extraction

    timm/eva02_base_patch14_224.mim_in22k

    10K
    6
    timm
    Sentence Similarity

    jinaai/jina-embeddings-v5-text-small-text-matching

    10K
    10
    llama.cpp
    Translation

    Helsinki-NLP/opus-mt-en-uk

    10K
    16
    transformers
    Fill Mask

    jplu/tf-xlm-roberta-base

    10K
    1
    transformers
    Robotics

    nvidia/GR00T-N1.7-3B

    10K
    18
    Fill Mask

    asafaya/bert-base-arabic

    10K
    40
    transformers
    Fill Mask

    dandelin/vilt-b32-mlm

    10K
    13
    transformers
    Sentence Similarity

    dragonkue/snowflake-arctic-embed-l-v2.0-ko

    10K
    46
    sentence-transformers
    Image To Text

    PaddlePaddle/SLANeXt_wired

    10K
    1
    PaddleOCR
    Automatic Speech Recognition

    NbAiLab/nb-whisper-large

    10K
    37
    transformers
    Feature Extraction

    perplexity-ai/pplx-embed-context-v1-0.6b

    10K
    52
    transformers
    Image To Image

    prithivMLmods/Qwen-Image-Edit-2511-Polaroid-Photo

    10K
    11
    diffusers
    143 / 376