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.

    17,271 models available

    Run models on your own files, freeSchedule DemoRead Documentation

    Showing 1-24 of 17,271 models

    Sentence Similarity

    sentence-transformers/all-MiniLM-L6-v2

    253.0M
    5,569
    sentence-transformers
    View Details
    Feature Extraction

    BAAI/bge-small-en-v1.5

    65.6M
    548
    sentence-transformers
    View Details
    Fill Mask

    google-bert/bert-base-uncased

    52.3M
    2,989
    transformers
    View Details
    Sentence Similarity

    sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

    46.3M
    1,367
    sentence-transformers
    View Details
    Sentence Similarity

    BAAI/bge-m3

    38.0M
    3,474
    sentence-transformers
    View Details
    Sentence Similarity

    sentence-transformers/all-mpnet-base-v2

    24.2M
    1,350
    sentence-transformers
    View Details
    Translation

    google-t5/t5-small

    23.4M
    598
    transformers
    View Details
    Text Generation

    Qwen/Qwen3-0.6B

    21.5M
    1,582
    transformers
    View Details
    Fill Mask

    FacebookAI/xlm-roberta-base

    21.4M
    895
    transformers
    View Details
    Zero Shot Image Classification

    openai/clip-vit-base-patch32

    20.6M
    1,211
    transformers
    View Details
    Text Classification

    BAAI/bge-reranker-v2-m3

    18.1M
    1,162
    sentence-transformers
    View Details
    Text Generation

    trl-internal-testing/tiny-Qwen2ForCausalLM-2.5

    17.6M
    21
    transformers
    View Details
    Image Classification

    timm/mobilenetv3_small_100.lamb_in1k

    17.2M
    103
    timm
    View Details
    Sentence Similarity

    nomic-ai/nomic-embed-text-v1.5

    16.4M
    901
    sentence-transformers
    View Details
    Text Generation

    openai-community/gpt2

    14.6M
    3,707
    transformers
    View Details
    Image Text To Text

    Qwen/Qwen3-VL-8B-Instruct

    13.9M
    1,082
    transformers
    View Details
    Automatic Speech Recognition

    jonatasgrosman/wav2vec2-large-xlsr-53-japanese

    13.5M
    63
    transformers
    View Details
    Feature Extraction

    BAAI/bge-large-en-v1.5

    13.3M
    720
    sentence-transformers
    View Details
    Text Generation

    Qwen/Qwen3-8B

    13.2M
    1,351
    transformers
    View Details
    Image Text To Text

    Qwen/Qwen3.6-35B-A3B-FP8

    12.9M
    376
    transformers
    View Details
    Text Generation

    unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF

    12.6M
    965
    transformers
    View Details
    Sentence Similarity

    intfloat/multilingual-e5-small

    12.1M
    398
    sentence-transformers
    View Details
    Image Classification

    timm/efficientnet_b3.ra2_in1k

    12.1M
    7
    timm
    View Details
    Image Text To Text

    Qwen/Qwen3.5-9B

    11.8M
    1,905
    transformers
    View Details
    1 / 720

    Choosing a model for multimodal retrieval

    Which of these models does Mixpeek actually run?

    Nine, and they are not the same thing as the catalog. The managed extractors run intfloat/multilingual-e5-large-instruct for text (1024-d), google/siglip-base-patch16-224 for images (768-d), google/vertex-multimodal (1408-d) and google/gemini-embedding-2 (3072-d) for unified multimodal, insightface ArcFace for faces (512-d), CLAP for audio fingerprints (512-d), facebook/dinov2-base for visual similarity and jinaai/jina-embeddings-v2-base-code for code (both 768-d, inside the web scraper). The rerank retriever stage runs BAAI/bge-reranker-v2-m3. Everything else in this catalog is documented here, not hosted here.

    Can I run any model from this catalog on Mixpeek?

    Not by naming it. No extractor takes a Hugging Face model id as a parameter, so there is no field to put one in. Three paths do work. Use a managed extractor and get the model it runs. Run the model on your own hardware and upsert the vectors through POST /v1/namespaces/{namespace_id}/documents/upsert, which stores them beside everything else. Or on Enterprise, upload the weights through POST /v1/namespaces/{namespace_id}/models, which accepts the huggingface format, and load them from a custom plugin.

    Should I use a text embedding model or a multimodal one?

    Ask whether a text query has to reach a non-text asset directly. If your video is searchable through its transcript and your images through their captions, a text model over that generated text is cheaper and usually more accurate, because retrieval quality on words is a solved problem and cross-modal alignment is not. If the query is 'find the shot that looks like this' or the visual content carries meaning no caption records, you need a shared space and a multimodal model. Most production systems run both indexes rather than choosing.

    What does the embedding dimension cost to store?

    A float32 vector is 4 bytes per dimension, so a million items costs 4 GB at 1024 dimensions, 3 GB at 768, and 12 GB at 3072. That is before any quantization and before payload. Models trained with Matryoshka representation learning, such as Gemini Embedding 2, let you truncate to a shorter prefix without re-encoding, so the width becomes an index-time decision rather than a model-selection one. Dimensions are fixed at namespace creation in Mixpeek, so changing a width later means re-indexing.

    Why does the download count on a model page differ from HuggingFace?

    It is the monthly figure from the HuggingFace API at the time of the last sync, not a live read, so it lags. The sync date is on each model page. Download count is a popularity signal and a poor quality signal: the most-downloaded model in a category is frequently an older checkpoint that a tutorial pinned years ago.

    Previous

    Connectors

    Next

    Retrievers

    What's new in models

    Full changelog

    All models

    Every model page in one place, 375 in total.