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 97-120 of 19,428 models

    Automatic Speech Recognition

    jonatasgrosman/wav2vec2-large-xlsr-53-polish

    3.3M
    25
    transformers
    View Details
    Image Text To Text

    Qwen/Qwen3.5-2B

    3.1M
    455
    transformers
    View Details
    Image Feature Extraction

    facebook/dinov2-base

    3.1M
    216
    transformers
    View Details
    Image Text To Text

    Qwen/Qwen3.8-Flash-Next

    3.1M
    6,482
    transformers
    View Details
    Image Text To Text

    microsoft/Florence-2-base

    3.1M
    431
    transformers
    View Details
    Automatic Speech Recognition

    jonatasgrosman/wav2vec2-large-xlsr-53-dutch

    3.0M
    28
    transformers
    View Details
    Any To Any

    google/gemma-4-E2B-it

    3.0M
    1,072
    transformers
    View Details
    Text Generation

    Qwen/Qwen3-32B

    2.9M
    772
    transformers
    View Details
    Text Classification

    BAAI/bge-reranker-base

    2.9M
    261
    sentence-transformers
    View Details
    Text Generation

    openai/gpt-oss-120b

    2.9M
    5,440
    transformers
    View Details
    Text Generation

    trl-internal-testing/tiny-Qwen2ForCausalLM-2.5

    2.8M
    59
    transformers
    View Details
    Text Generation

    deepreinforce-ai/Ornith-1.0-35B

    2.7M
    462
    transformers
    View Details
    Sentence Similarity

    sentence-transformers/all-distilroberta-v1

    2.7M
    54
    sentence-transformers
    View Details
    Automatic Speech Recognition

    jonatasgrosman/wav2vec2-large-xlsr-53-greek

    2.7M
    13
    transformers
    View Details
    Image Feature Extraction

    facebook/dinov2-small

    2.7M
    86
    transformers
    View Details
    Zero Shot Image Classification

    openai/clip-vit-large-patch14-336

    2.7M
    326
    transformers
    View Details
    Fill Mask

    microsoft/deberta-v3-base

    2.6M
    468
    transformers
    View Details
    Sentence Similarity

    sentence-transformers/all-MiniLM-L12-v2

    2.6M
    348
    sentence-transformers
    View Details
    Image Text To Text

    cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF

    2.6M
    44
    View Details
    Automatic Speech Recognition

    mlx-community/parakeet-tdt-0.6b-v3

    2.6M
    69
    mlx
    View Details
    Automatic Speech Recognition

    jonatasgrosman/wav2vec2-large-xlsr-53-arabic

    2.6M
    68
    transformers
    View Details
    Text Classification

    distilbert/distilbert-base-uncased-finetuned-sst-2-english

    2.6M
    990
    transformers
    View Details
    Sentence Similarity

    Snowflake/snowflake-arctic-embed-l-v2.0

    2.6M
    265
    sentence-transformers
    View Details
    Text Generation

    Qwen/Qwen3-4B-Instruct-2507

    2.6M
    1,029
    transformers
    View Details
    5 / 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.