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 745768 of 9,002 models

    Feature Extraction

    descript/dac_44khz

    308K
    11
    transformers
    Image Classification

    microsoft/resnet-50

    308K
    492
    transformers
    Image Text To Text

    Qwen/Qwen3.5-122B-A10B-GPTQ-Int4

    307K
    38
    transformers
    Text Classification

    cardiffnlp/twitter-xlm-roberta-base-sentiment-multilingual

    307K
    31
    transformers
    Automatic Speech Recognition

    Khalsuu/filipino-wav2vec2-l-xls-r-300m-official

    307K
    2
    transformers
    Feature Extraction

    microsoft/codebert-base

    306K
    285
    transformers
    Image Text To Text

    reducto/RolmOCR

    305K
    585
    transformers
    Text Classification

    mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis

    304K
    453
    transformers
    Image Text To Text

    bartowski/google_gemma-4-31B-it-GGUF

    304K
    57
    Automatic Speech Recognition

    t-tech/T-one

    303K
    90
    Fill Mask

    tohoku-nlp/bert-base-japanese-whole-word-masking

    303K
    76
    transformers
    Text Generation

    Qwen/Qwen2.5-Coder-7B-Instruct-AWQ

    303K
    22
    transformers
    Text Generation

    state-spaces/mamba-130m-hf

    302K
    70
    transformers
    Automatic Speech Recognition

    CohereLabs/cohere-transcribe-03-2026

    302K
    913
    transformers
    Image Text To Text

    bartowski/Qwen_Qwen3.5-35B-A3B-GGUF

    301K
    63
    Text Classification

    jason9693/Qwen2.5-1.5B-apeach

    301K
    5
    transformers
    Image Classification

    timm/vit_base_patch16_224.augreg_in21k

    300K
    11
    timm
    Question Answering

    deepset/roberta-large-squad2

    299K
    29
    transformers
    Text Generation

    naver-hyperclovax/HyperCLOVAX-SEED-Omni-8B

    299K
    186
    transformers
    Image Text To Text

    unsloth/Qwen3.5-0.8B-GGUF

    299K
    146
    transformers
    Image Text To Text

    google/gemma-3n-E2B-it

    299K
    296
    transformers
    Text Classification

    E-MIMIC/inclusively-classification

    299K
    1
    transformers
    Token Classification

    dslim/distilbert-NER

    299K
    51
    transformers
    Image Text To Text

    OpenGVLab/InternVL2_5-8B

    298K
    104
    transformers
    32 / 376