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.

    19,428 models available

    Run models on your own files, freeSchedule DemoRead Documentation

    Showing 25-48 of 19,428 models

    Fill Mask

    FacebookAI/xlm-roberta-base

    8.2M
    963
    transformers
    View Details
    Feature Extraction

    Qwen/Qwen3-Embedding-0.6B

    8.2M
    1,310
    sentence-transformers
    View Details
    Image Text To Text

    google/gemma-4-26B-A4B-it

    8.2M
    1,701
    transformers
    View Details
    Text Generation

    Qwen/Qwen3-8B

    8.1M
    2,145
    transformers
    View Details
    Image Text To Text

    Qwen/Qwen3.8-27B

    7.8M
    18,412
    transformers
    View Details
    Image Text To Text

    Qwen/Qwen3.5-4B

    7.4M
    1,129
    transformers
    View Details
    Object Detection

    mudler/locate-anything.cpp-gguf

    7.3M
    69
    gguf
    View Details
    Image Classification

    prithivMLmods/Gender-Classifier-Mini

    7.2M
    14
    transformers
    View Details
    Audio Classification

    laion/clap-htsat-fused

    7.1M
    174
    transformers
    View Details
    Text To Speech

    audio-cpp/audio.cpp-gguf

    6.9M
    274
    audio.cpp
    View Details
    Fill Mask

    FacebookAI/roberta-large

    6.9M
    345
    transformers
    View Details
    Automatic Speech Recognition

    pyannote/speaker-diarization-3.1

    6.9M
    4,628
    pyannote-audio
    View Details
    Image Text To Text

    ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF

    6.9M
    1,027
    gguf
    View Details
    Fill Mask

    FacebookAI/roberta-base

    6.5M
    699
    transformers
    View Details
    Feature Extraction

    intfloat/multilingual-e5-large

    6.5M
    1,281
    sentence-transformers
    View Details
    Zero Shot Image Classification

    openai/clip-vit-large-patch14

    6.5M
    2,134
    transformers
    View Details
    Image Text To Text

    zai-org/GLM-5.3-Flash

    6.4M
    2,947
    transformers
    View Details
    Fill Mask

    distilbert/distilbert-base-uncased

    6.3M
    1,136
    transformers
    View Details
    Feature Extraction

    ibm-granite/granite-embedding-small-english-r2

    6.2M
    111
    sentence-transformers
    View Details
    Text To Speech

    coqui/XTTS-v2

    6.1M
    3,914
    coqui
    View Details
    Image Text To Text

    Qwen/Qwen3.5-9B

    6.1M
    2,242
    transformers
    View Details
    Automatic Speech Recognition

    openai/whisper-large-v3-turbo

    5.8M
    3,478
    transformers
    View Details
    Text Generation

    openai/gpt-oss-20b

    5.8M
    5,220
    transformers
    View Details
    Text Generation

    Qwen/Qwen2.5-7B-Instruct

    5.7M
    2,458
    transformers
    View Details
    2 / 810

    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, 440 in total.