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 15851608 of 9,002 models

    Text Generation

    google/gemma-3-270m

    99K
    1,018
    transformers
    Text To Image

    optimum-intel-internal-testing/tiny-random-latent-consistency

    99K
    diffusers
    Text Classification

    ignacio-ave/beto-sentiment-analysis-spanish

    99K
    6
    transformers
    Feature Extraction

    farbodtavakkoli/OTel-Embedding-0.6B

    99K
    Zero Shot Image Classification

    google/siglip2-giant-opt-patch16-384

    99K
    41
    transformers
    Text Generation

    moonshotai/Kimi-K2-Thinking

    98K
    1,697
    transformers
    Text Generation

    trl-internal-testing/tiny-FalconMambaForCausalLM

    98K
    transformers
    Text Generation

    unsloth/MiniMax-M2.5-GGUF

    98K
    233
    transformers
    Text Classification

    w11wo/indonesian-roberta-base-sentiment-classifier

    98K
    54
    transformers
    Fill Mask

    nlpaueb/bert-base-uncased-contracts

    98K
    31
    transformers
    Zero Shot Image Classification

    timm/ViT-B-16-SigLIP

    98K
    37
    open_clip
    Text Generation

    unsloth/Qwen3-4B-Instruct-2507

    98K
    26
    transformers
    Text Classification

    vijil/vijil_dome_toxic_content_detection

    98K
    transformers
    Text Generation

    unsloth/Qwen2.5-0.5B-Instruct

    98K
    12
    transformers
    Fill Mask

    UBC-NLP/MARBERTv2

    98K
    14
    transformers
    Image Text To Text

    google/medgemma-1.5-4b-it

    98K
    590
    transformers
    Text Generation

    ggml-org/stories15M_MOE

    97K
    6
    transformers
    Translation

    facebook/mbart-large-50-many-to-many-mmt

    97K
    408
    transformers
    Zero Shot Image Classification

    timm/vit_base_patch16_clip_224.metaclip_2pt5b

    97K
    1
    open_clip
    Image Text To Text

    HuggingFaceTB/SmolVLM-500M-Instruct

    97K
    192
    transformers
    Image Classification

    Organika/sdxl-detector

    97K
    53
    transformers
    Text Generation

    Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8

    97K
    150
    transformers
    Feature Extraction

    farbodtavakkoli/OTel-Embedding-4B

    97K
    Fill Mask

    albert/albert-base-v1

    97K
    13
    transformers
    67 / 376