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 145-168 of 19,428 models

    Text Generation

    deepreinforce-ai/Ornith-1.0-9B

    2.3M
    502
    transformers
    View Details
    Fill Mask

    emilyalsentzer/Bio_ClinicalBERT

    2.2M
    450
    transformers
    View Details
    Text Generation

    prism-ml/Ternary-Bonsai-2-27B-gguf

    2.2M
    2,828
    llama.cpp
    View Details
    Text To Speech

    k2-fsa/OmniVoice

    2.2M
    1,594
    omnivoice
    View Details
    Text Generation

    Qwen/Qwen3-8B-AWQ

    2.2M
    68
    transformers
    View Details
    Text Classification

    Arunavaonly/Bangla-twoclass-Sentiment-Analyzer

    2.1M
    11
    transformers
    View Details
    Text Classification

    daekeun-ml/koelectra-small-v3-nsmc

    2.1M
    7
    transformers
    View Details
    Feature Extraction

    mixedbread-ai/mxbai-embed-large-v1

    2.1M
    845
    sentence-transformers
    View Details
    Text Generation

    zai-org/GLM-5.3

    2.1M
    2,310
    transformers
    View Details
    Image Text To Text

    deepseek-ai/DeepSeek-OCR

    2.1M
    3,457
    transformers
    View Details
    Image Feature Extraction

    timm/vit_small_patch14_dinov2.lvd142m

    2.1M
    15
    timm
    View Details
    Image Text To Text

    RedHatAI/gemma-4-26B-A4B-it-FP8-Dynamic

    2.1M
    32
    transformers
    View Details
    Image Classification

    timm/tf_efficientnetv2_s.in21k_ft_in1k

    2.1M
    15
    timm
    View Details
    Automatic Speech Recognition

    mistralai/Voxtral-Mini-4B-Realtime-2602

    2.0M
    1,046
    vllm
    View Details
    Image Classification

    timm/resnet18.a1_in1k

    2.0M
    30
    timm
    View Details
    Text To Image

    stabilityai/stable-diffusion-xl-base-1.0

    2.0M
    7,663
    diffusers
    View Details
    Automatic Speech Recognition

    handy-computer/parakeet-unified-en-0.6b-gguf

    2.0M
    19
    transcribe.cpp
    View Details
    Automatic Speech Recognition

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

    2.0M
    27
    transcribe.cpp
    View Details
    Image Text To Text

    byteshape/Qwen3.8-27B-GGUF

    2.0M
    182
    transformers
    View Details
    Text Generation

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

    2.0M
    60
    transformers
    View Details
    Text Generation

    HuggingFaceTB/SmolLM2-135M

    2.0M
    261
    transformers
    View Details
    Feature Extraction

    Qwen/Qwen3-Embedding-8B

    2.0M
    840
    sentence-transformers
    View Details
    Translation

    google-t5/t5-base

    2.0M
    805
    transformers
    View Details
    Feature Extraction

    BAAI/bge-reranker-large

    1.9M
    484
    transformers
    View Details
    7 / 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, 442 in total.