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 193-216 of 17,271 models

    Feature Extraction

    intfloat/multilingual-e5-large-instruct

    2.0M
    635
    sentence-transformers
    View Details
    Image Text To Text

    Qwen/Qwen2-VL-2B-Instruct

    2.0M
    518
    transformers
    View Details
    Text Generation

    Qwen/Qwen3-4B-Base

    2.0M
    97
    transformers
    View Details
    Text Generation

    distilbert/distilgpt2

    2.0M
    640
    transformers
    View Details
    Image Text To Text

    llava-hf/llava-1.5-7b-hf

    1.9M
    372
    transformers
    View Details
    Feature Extraction

    BAAI/bge-base-en

    1.9M
    62
    transformers
    View Details
    Text To Audio

    facebook/musicgen-medium

    1.9M
    167
    transformers
    View Details
    Image Classification

    timm/resnet50.a1_in1k

    1.9M
    43
    timm
    View Details
    Text Generation

    Qwen/Qwen2.5-Coder-14B-Instruct

    1.9M
    184
    transformers
    View Details
    Automatic Speech Recognition

    kingabzpro/wav2vec2-large-xls-r-300m-Urdu

    1.9M
    14
    transformers
    View Details
    Text Generation

    zai-org/GLM-4.7-Flash

    1.9M
    1,832
    transformers
    View Details
    Image Classification

    dima806/fairface_age_image_detection

    1.9M
    81
    transformers
    View Details
    Text Generation

    Qwen/Qwen3-1.7B-Base

    1.9M
    78
    transformers
    View Details
    Sentence Similarity

    sentence-transformers/paraphrase-mpnet-base-v2

    1.9M
    50
    sentence-transformers
    View Details
    Automatic Speech Recognition

    comodoro/wav2vec2-xls-r-300m-cs-250

    1.9M
    3
    transformers
    View Details
    Image Classification

    timm/tf_efficientnetv2_s.in21k_ft_in1k

    1.9M
    4
    timm
    View Details
    Sentence Similarity

    intfloat/e5-large-v2

    1.8M
    283
    sentence-transformers
    View Details
    Token Classification

    StanfordAIMI/stanford-deidentifier-base

    1.8M
    85
    transformers
    View Details
    Text Generation

    Qwen/Qwen2.5-Coder-14B-Instruct-AWQ

    1.8M
    24
    transformers
    View Details
    Image Text To Text

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

    1.8M
    105
    transformers
    View Details
    Depth Estimation

    depth-anything/Depth-Anything-V2-Small-hf

    1.8M
    46
    transformers
    View Details
    Image To Text

    Salesforce/blip-image-captioning-base

    1.8M
    887
    transformers
    View Details
    Text Generation

    nvidia/Gemma-4-31B-IT-NVFP4

    1.8M
    563
    Model Optimizer
    View Details
    Automatic Speech Recognition

    handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf

    1.8M
    8
    transcribe.cpp
    View Details
    9 / 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.