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.

    9,588 models available

    Showing 66256648 of 9,588 models

    Zero Shot Image Classification

    visheratin/mexma-siglip2

    325
    14
    Object Detection

    merve/license-plate-detr-dinov3

    324
    1
    transformers
    Audio Classification

    GradientDescent2718/ls-eend-coreml

    323
    coreml
    Image To Text

    EZCon/GLM-OCR-4bit-mlx

    322
    mlx
    Image Feature Extraction

    timm/convnext_large_mlp.clip_laion2b_augreg

    322
    timm
    Audio Classification

    superb/wav2vec2-base-superb-ic

    322
    transformers
    Depth Estimation

    depth-anything/prompt-depth-anything-vitl-hf

    321
    2
    transformers
    Object Detection

    mlx-community/YOLO26x-OptiQ-6bit

    321
    2
    mlx
    Zero Shot Image Classification

    AoiNoGeso/japanese-clip-stair

    321
    transformers
    Image To Text

    manu02/LAnA-v5

    321
    transformers
    Audio Classification

    speechbrain/emotion-diarization-wavlm-large

    320
    56
    speechbrain
    Question Answering

    QuantFactory/SuperCorrect-7B-GGUF

    320
    2
    transformers
    Summarization

    ELiRF/NASES

    319
    3
    transformers
    Visual Question Answering

    prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF

    319
    3
    transformers
    Image To Text

    katanaml-org/invoices-donut-model-v1

    319
    40
    transformers
    Image Feature Extraction

    matybohacek/RA-SAE-DINOv2-32k

    319
    Visual Question Answering

    microsoft/git-base-vqav2

    318
    21
    transformers
    Image Feature Extraction

    tiiuae/siglino-70M

    318
    6
    transformers
    Text To Video

    Skywork/SkyReels-V2-T2V-14B-720P

    318
    42
    diffusers
    Question Answering

    ZeyadAhmed/AraElectra-Arabic-SQuADv2-QA

    317
    18
    transformers
    Robotics

    nvidia/smolvla-arena-gr1-microwave

    316
    lerobot
    Text To Video

    wangkanai/wan22-fp16-encoders-gguf

    315
    3
    diffusers
    Summarization

    phh/Qwen3-0.6B-TLDR-Lora

    314
    peft
    Audio To Audio

    mpariente/DPRNNTasNet-ks2_WHAM_sepclean

    314
    9
    asteroid
    277 / 400