Mage-VL
by microsoft
Vision-language model built for streaming video rather than single frames
microsoft/Mage-VLOverview
Most vision-language models take one image and some text. Mage-VL is tagged for video understanding and streaming, which is a different problem: the input keeps arriving, and the model has to stay useful without re-reading everything it has already seen.
That matters for anyone indexing video, because the naive approach is to sample frames, embed each one independently, and lose every relationship between them. A model that consumes a stream can describe what changed, not just what is present.
At 4.7B parameters under Apache 2.0 it sits in the range you can self-host. Treat it as a describer and a reranker rather than a first-pass indexer: generating text for every frame of a large archive is expensive, and a cheap embedding model is the right thing to run first.
Architecture
MageVLForConditionalGeneration, model type mage_vl, 4,741,793,792 parameters. Image-text-to-text pipeline with video-understanding and streaming support declared on the model card. Requires trust_remote_code.
Key Capabilities
- •Describing video segments in natural language
- •Question answering grounded in visual content
- •Streaming input rather than fixed-length clips
- •Generating text metadata for otherwise unlabelled footage
Use Cases on Mixpeek
- •Writing searchable descriptions for archive footage that has no captions
- •Answering questions about a video without a human watching it
- •Producing the text side of a hybrid index, where BM25 needs something to match
- •Reranking a shortlist of clips returned by a cheaper embedding model
Tags
Use Mage-VL on Mixpeek
Build multimodal processing pipelines with this model and others. Extract features, run inference, and set up retrieval in Mixpeek Studio.
Open StudioHow It Runs on Mixpeek
On Mixpeek, Mage-VL runs as a managed extractor inside a processing pipeline. Point a bucket of image text to text data at it, and Mixpeek handles GPU provisioning, batching, retries, and writing the outputs into a vector store you can query.
Extractor outputs land in the Mixpeek Vector Store (MVS), where you can combine them with retrieval, reranking, and filter stages to build end-to-end search and agent-perception pipelines, no model-serving infrastructure to maintain.
Explore on Mixpeek
Compare alternatives in this category
Hand-picked tools & platforms compared
Deep-dive technical guide
See how Mixpeek runs models as extractors
Store & search embeddings at scale
Usage-based pricing for pipelines
Compare models, APIs & infrastructure
Specification
View on HuggingFace
See model card, files, and community discussion