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 49-72 of 19,428 models

    Text Generation

    deepseek-ai/DeepSeek-V3.2

    5.6M
    1,587
    transformers
    View Details
    Image Text To Text

    Qwen/Qwen3-VL-8B-Instruct

    5.5M
    1,224
    transformers
    View Details
    Fill Mask

    microsoft/mdeberta-v3-base

    5.5M
    260
    transformers
    View Details
    Sentence Similarity

    intfloat/multilingual-e5-base

    5.5M
    415
    sentence-transformers
    View Details
    Text Generation

    facebook/opt-125m

    5.2M
    332
    transformers
    View Details
    Text Generation

    Qwen/Qwen2.5-0.5B-Instruct

    5.2M
    713
    transformers
    View Details
    Voice Activity Detection

    pyannote/segmentation-3.0

    5.2M
    2,383
    pyannote-audio
    View Details
    Image Text To Text

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

    5.1M
    1,754
    transformers
    View Details
    Text Generation

    ornith-ai/Ornith-1.5-9B-GGUF

    5.1M
    596
    transformers
    View Details
    Automatic Speech Recognition

    pyannote/speaker-diarization-community-1

    5.0M
    3,384
    pyannote-audio
    View Details
    Automatic Speech Recognition

    Systran/faster-whisper-small

    4.8M
    82
    ctranslate2
    View Details
    Text Generation

    meta-llama/Llama-3.1-8B-Instruct

    4.8M
    8,610
    transformers
    View Details
    Text Classification

    SamLowe/roberta-base-go_emotions

    4.8M
    715
    transformers
    View Details
    Text Generation

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

    4.7M
    599
    transformers
    View Details
    Text Generation

    dphn/dolphin-2.9.1-yi-1.5-34b

    4.6M
    86
    transformers
    View Details
    Text Generation

    Qwen/Qwen2.5-1.5B-Instruct

    4.6M
    913
    transformers
    View Details
    Fill Mask

    facebook/esm2_t33_650M_UR50D

    4.5M
    105
    transformers
    View Details
    Image Text To Text

    Qwen/Qwen3.8-27B-FP8

    4.4M
    945
    transformers
    View Details
    Feature Extraction

    Xenova/all-MiniLM-L6-v2

    4.3M
    174
    transformers.js
    View Details
    Text Generation

    nvidia/Qwen3.6-35B-A3B-NVFP4

    4.1M
    671
    Model Optimizer
    View Details
    Text Generation

    deepseek-ai/DeepSeek-V4-Flash-0731

    4.1M
    4,090
    transformers
    View Details
    Text Generation

    Qwen/Qwen3-1.7B

    4.1M
    594
    transformers
    View Details
    Zero Shot Image Classification

    laion/CLIP-ViT-B-32-laion2B-s34B-b79K

    4.1M
    155
    open_clip
    View Details
    Automatic Speech Recognition

    jonatasgrosman/wav2vec2-large-xlsr-53-portuguese

    4.0M
    71
    transformers
    View Details
    3 / 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.