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.

    12,152 models available

    Showing 7396 of 12,152 models

    Text Generation

    openai/gpt-oss-120b

    4.5M
    4,859
    transformers
    Feature Extraction

    facebook/w2v-bert-2.0

    4.4M
    217
    transformers
    Fill Mask

    facebook/esm2_t33_650M_UR50D

    4.3M
    80
    transformers
    Text Generation

    distilbert/distilgpt2

    4.3M
    630
    transformers
    Text Generation

    Qwen/Qwen2.5-0.5B-Instruct

    4.3M
    526
    transformers
    Image Text To Text

    zai-org/GLM-OCR

    4.2M
    1,815
    transformers
    Fill Mask

    google-bert/bert-base-multilingual-uncased

    4.2M
    157
    transformers
    Automatic Speech Recognition

    openai/whisper-base

    4.2M
    271
    transformers
    Text Classification

    BAAI/bge-reranker-base

    4.2M
    236
    sentence-transformers
    Text Generation

    Qwen/Qwen2-1.5B-Instruct

    4.2M
    162
    transformers
    Text Generation

    hmellor/tiny-random-LlamaForCausalLM

    4.2M
    transformers
    Text Generation

    deepseek-ai/DeepSeek-V3.2

    4.1M
    1,445
    transformers
    Fill Mask

    google-bert/bert-base-cased

    4.0M
    360
    transformers
    Feature Extraction

    BAAI/bge-small-zh-v1.5

    3.9M
    116
    transformers
    Image Text To Text

    Qwen/Qwen3-VL-4B-Instruct

    3.9M
    394
    transformers
    Image Text To Text

    Qwen/Qwen2-VL-2B-Instruct

    3.9M
    506
    transformers
    Fill Mask

    google-bert/bert-base-multilingual-cased

    3.8M
    592
    transformers
    Text Generation

    Qwen/Qwen3-32B

    3.8M
    699
    transformers
    Feature Extraction

    jinaai/jina-embeddings-v3

    3.8M
    1,144
    transformers
    Image Classification

    timm/convnextv2_nano.fcmae_ft_in22k_in1k

    3.7M
    4
    timm
    Text Classification

    cardiffnlp/twitter-roberta-base-sentiment-latest

    3.7M
    806
    transformers
    Voice Activity Detection

    pyannote/segmentation

    3.7M
    677
    pyannote-audio
    Image Classification

    apple/mobilevit-small

    3.6M
    91
    transformers
    Feature Extraction

    Xenova/all-MiniLM-L6-v2

    3.6M
    121
    transformers.js
    4 / 507