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 169-192 of 19,428 models

    Text To Speech

    Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

    1.9M
    2,175
    View Details
    Text To Audio

    facebook/musicgen-medium

    1.9M
    176
    transformers
    View Details
    Text To Speech

    ResembleAI/chatterbox

    1.9M
    1,866
    chatterbox
    View Details
    Text Generation

    CMSManhattan/JiRackUltra_1b

    1.9M
    15
    View Details
    Automatic Speech Recognition

    jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn

    1.9M
    145
    transformers
    View Details
    Image Text To Text

    DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF

    1.9M
    1,209
    View Details
    Feature Extraction

    Qwen/Qwen3-Embedding-4B

    1.8M
    342
    sentence-transformers
    View Details
    Zero Shot Image Classification

    laion/CLIP-convnext_base_w-laion2B-s13B-b82K-augreg

    1.8M
    20
    open_clip
    View Details
    Sentence Similarity

    Alibaba-NLP/gte-large-en-v1.5

    1.8M
    251
    transformers
    View Details
    Text Generation

    mistralai/Mistral-7B-Instruct-v0.2

    1.8M
    3,271
    transformers
    View Details
    Image Text To Text

    Qwen/Qwen3-VL-2B-Instruct

    1.8M
    505
    transformers
    View Details
    Text Generation

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

    1.8M
    206
    transformers
    View Details
    Automatic Speech Recognition

    facebook/wav2vec2-base-960h

    1.8M
    413
    transformers
    View Details
    Automatic Speech Recognition

    KBLab/wav2vec2-large-voxrex-swedish

    1.8M
    25
    transformers
    View Details
    Image Text To Text

    Qwen/Qwen3.5-27B

    1.7M
    1,074
    transformers
    View Details
    Automatic Speech Recognition

    Systran/faster-whisper-base

    1.7M
    50
    ctranslate2
    View Details
    Any To Any

    google/gemma-4-12B-it

    1.7M
    1,690
    transformers
    View Details
    Zero Shot Image Classification

    google/siglip2-giant-opt-patch16-384

    1.7M
    56
    transformers
    View Details
    Feature Extraction

    intfloat/multilingual-e5-large-instruct

    1.7M
    655
    sentence-transformers
    View Details
    Automatic Speech Recognition

    openai/whisper-base

    1.7M
    311
    transformers
    View Details
    Image To Text

    zai-org/GLM-OCR

    1.7M
    2,181
    transformers
    View Details
    Image Text To Text

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

    1.7M
    118
    transformers
    View Details
    Image Text To Text

    DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF

    1.7M
    2,092
    View Details
    Sentence Similarity

    Qdrant/all-MiniLM-L6-v2-onnx

    1.7M
    28
    transformers
    View Details
    8 / 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.