NEWVectors or files. Pick a path.Start →

    AI Model Hub

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

    14,077 models available

    Get startedSchedule DemoRead Documentation

    Showing 8137–8160 of 14,077 models

    Any To Any

    vanch007/gemma-4-E4B-it-heretic-mlx-nvfp4

    500
    mlx
    View Details
    Reinforcement Learning

    mradermacher/ProtoCycle-7B-GGUF

    499
    1
    transformers
    View Details
    Question Answering

    SkelterLabsInc/bert-base-japanese-jaquad

    499
    2
    transformers
    View Details
    Question Answering

    Jacaranda/AfroLlama_V1

    499
    9
    transformers
    View Details
    Image Segmentation

    facebook/mask2former-swin-large-cityscapes-panoptic

    498
    3
    transformers
    View Details
    Question Answering

    DragonLLM/Qwen-Open-Finance-R-8B-FP8

    497
    1
    transformers
    View Details
    Audio To Audio

    NandemoGHS/Anime-XCodec2

    496
    17
    View Details
    Image Segmentation

    qualcomm/DeepLabV3-Plus-MobileNet

    496
    1
    pytorch
    View Details
    Image To Text

    Abiray/Qianfan-OCR-GGUF

    496
    1
    gguf
    View Details
    Image To Text

    axelbrons/gemma-4-E4B-it-Q4_K_M-v2

    496
    1
    View Details
    Audio To Audio

    slprl/SIMS-Llama3.2-3B

    494
    2
    transformers
    View Details
    Audio Classification

    anton-l/wav2vec2-base-superb-sv

    494
    3
    transformers
    View Details
    Image Feature Extraction

    facebook/sapiens2-pretrain-0.1b

    494
    7
    sapiens2
    View Details
    Image To Text

    microsoft/git-large-textcaps

    493
    31
    transformers
    View Details
    Audio To Audio

    jhcodec/jhcodec

    492
    4
    View Details
    Unconditional Image Generation

    google/ddpm-ema-church-256

    492
    15
    diffusers
    View Details
    Image Segmentation

    ZhengPeng7/BiRefNet-legacy

    492
    2
    birefnet
    View Details
    Reinforcement Learning

    Sepolian/qwen2.5-0.5B-math

    492
    transformers
    View Details
    Image To Text

    ShayanCyan/phi4-multimodal-quantisized-gguf

    491
    6
    other
    View Details
    Text To Video

    vrgamedevgirl84/LTX_2.3_Cinematic_Sci-fi-Cyberpunk_Style_LoRa

    491
    9
    diffusers
    View Details
    Object Detection

    rudrasinghm/dfine-football-detector

    491
    1
    transformers
    View Details
    Reinforcement Learning

    mradermacher/LongTraceRL-30B-i1-GGUF

    490
    transformers
    View Details
    Any To Any

    cyankiwi/Qwen3-Omni-30B-A3B-Thinking-AWQ-8bit

    489
    1
    transformers
    View Details
    Zero Shot Classification

    cointegrated/rubert-tiny-bilingual-nli

    488
    8
    transformers
    View Details
    340 / 587

    Previous

    Connectors

    Next

    Retrievers

    What's new in models

    Full changelog