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 121-144 of 19,428 models

    Image Text To Text

    baidu/Unlimited-OCR

    2.6M
    4,896
    transformers
    View Details
    Image Text To Text

    huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF

    2.6M
    1,506
    transformers
    View Details
    Image Text To Text

    SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF

    2.5M
    435
    gguf
    View Details
    Image Text To Text

    autotrust/JEV-27B-VL

    2.5M
    1,538
    transformers
    View Details
    Feature Extraction

    BAAI/bge-base-en

    2.5M
    72
    transformers
    View Details
    Text Generation

    Qwen/Qwen3-14B-AWQ

    2.4M
    88
    transformers
    View Details
    Automatic Speech Recognition

    indonesian-nlp/wav2vec2-indonesian-javanese-sundanese

    2.4M
    24
    transformers
    View Details
    Text Generation

    JonathanColetti/Qwen3.8-27B-Uncensored-GGUF

    2.4M
    1,742
    llama.cpp
    View Details
    Text Classification

    meta-llama/Prompt-Guard-86M

    2.4M
    428
    transformers
    View Details
    Text Generation

    ornith-ai/Ornith-1.0-9B-GGUF

    2.4M
    696
    transformers
    View Details
    Image Text To Text

    Qwen/Qwen3.6-27B

    2.4M
    2,338
    transformers
    View Details
    Fill Mask

    FacebookAI/xlm-roberta-large

    2.4M
    553
    transformers
    View Details
    Text Classification

    cardiffnlp/twitter-roberta-base-sentiment-latest

    2.4M
    853
    transformers
    View Details
    Zero Shot Classification

    facebook/bart-large-mnli

    2.4M
    1,632
    transformers
    View Details
    Feature Extraction

    Xenova/bge-base-en-v1.5

    2.4M
    27
    transformers.js
    View Details
    Image Text To Text

    vikhyatk/moondream2

    2.3M
    1,446
    transformers
    View Details
    Automatic Speech Recognition

    MahmoudAshraf/mms-300m-1130-forced-aligner

    2.3M
    118
    transformers
    View Details
    Automatic Speech Recognition

    jonatasgrosman/wav2vec2-large-xlsr-53-hungarian

    2.3M
    16
    transformers
    View Details
    Image Text To Text

    HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF

    2.3M
    2,095
    View Details
    Sentence Similarity

    google/embeddinggemma-300m

    2.3M
    2,061
    sentence-transformers
    View Details
    Automatic Speech Recognition

    Systran/faster-whisper-tiny

    2.3M
    35
    ctranslate2
    View Details
    Image Text To Text

    peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP

    2.3M
    308
    gguf
    View Details
    Image Text To Text

    ggml-org/Qwen3.8-27B-GGUF

    2.3M
    139
    View Details
    Audio Classification

    audeering/wav2vec2-large-robust-24-ft-age-gender

    2.3M
    84
    transformers
    View Details
    6 / 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.