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.

    17,271 models available

    Run models on your own files, freeSchedule DemoRead Documentation

    Showing 145-168 of 17,271 models

    Text Classification

    trl-internal-testing/tiny-Qwen2ForSequenceClassification-2.5

    2.5M
    1
    transformers
    View Details
    Text Classification

    daekeun-ml/koelectra-small-v3-nsmc

    2.5M
    7
    transformers
    View Details
    Text Generation

    google/gemma-3-1b-it

    2.5M
    1,133
    transformers
    View Details
    Text Generation

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

    2.5M
    1,004
    llama.cpp
    View Details
    Image Text To Text

    moonshotai/Kimi-K3

    2.5M
    11,220
    transformers
    View Details
    Image Text To Text

    deepseek-ai/DeepSeek-OCR

    2.4M
    3,351
    transformers
    View Details
    Image Text To Text

    Qwen/Qwen3.5-0.8B

    2.4M
    698
    transformers
    View Details
    Image Text To Text

    Qwen/Qwen3.5-35B-A3B

    2.4M
    1,500
    transformers
    View Details
    Audio Classification

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

    2.3M
    59
    transformers
    View Details
    Image Text To Text

    Qwen/Qwen3-VL-8B-Instruct-FP8

    2.3M
    82
    transformers
    View Details
    Token Classification

    w11wo/indonesian-roberta-base-posp-tagger

    2.3M
    10
    transformers
    View Details
    Feature Extraction

    Xenova/bge-base-en-v1.5

    2.3M
    10
    transformers.js
    View Details
    Sentence Similarity

    google/embeddinggemma-300m

    2.3M
    1,886
    sentence-transformers
    View Details
    Feature Extraction

    jinaai/jina-embeddings-v3

    2.3M
    1,154
    transformers
    View Details
    Image Text To Text

    Qwen/Qwen3.5-27B

    2.3M
    1,040
    transformers
    View Details
    Feature Extraction

    facebook/w2v-bert-2.0

    2.3M
    228
    transformers
    View Details
    Text Generation

    nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16

    2.3M
    116
    transformers
    View Details
    Text Generation

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

    2.3M
    792
    transformers
    View Details
    Automatic Speech Recognition

    gigant/romanian-wav2vec2

    2.3M
    8
    transformers
    View Details
    Text Generation

    Qwen/Qwen3-14B-AWQ

    2.3M
    73
    transformers
    View Details
    Sentence Similarity

    nomic-ai/nomic-embed-text-v2-moe

    2.3M
    498
    sentence-transformers
    View Details
    Automatic Speech Recognition

    Systran/faster-whisper-small

    2.3M
    47
    ctranslate2
    View Details
    Image Text To Text

    cyankiwi/gemma-4-26B-A4B-it-AWQ-4bit

    2.3M
    95
    transformers
    View Details
    Text Generation

    deepreinforce-ai/Ornith-1.0-9B

    2.3M
    502
    transformers
    View Details
    7 / 720

    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, 375 in total.