# SmolVLM2: Bringing Video Understanding to Every Device

DevFeed: [SmolVLM2: Bringing Video Understanding to Every Device](<https://devfeed.tech/articles/smolvlm2-bringing-video-understanding-to-every-device-7485.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/smolvlm2>)

Author: Orr Zohar; Miquel Farré; Andres Marafioti; merve; Pedro Cuenca; Cyril; Joshua

Published: 2025-02-20T00:00:00Z

Content type: release

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [Language models](<https://devfeed.tech/topics/language-models.md>)

Tags: [apis](<https://devfeed.tech/tags/apis.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [devices](<https://devfeed.tech/tags/devices.md>), [images](<https://devfeed.tech/tags/images.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [llm](<https://devfeed.tech/tags/llm.md>), [memory](<https://devfeed.tech/tags/memory.md>), [mlx](<https://devfeed.tech/tags/mlx.md>), [models](<https://devfeed.tech/tags/models.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [nlp](<https://devfeed.tech/tags/nlp.md>), [on-device](<https://devfeed.tech/tags/on-device.md>), [performance](<https://devfeed.tech/tags/performance.md>), [python](<https://devfeed.tech/tags/python.md>), [release](<https://devfeed.tech/tags/release.md>), [swift](<https://devfeed.tech/tags/swift.md>), [video](<https://devfeed.tech/tags/video.md>), [vision](<https://devfeed.tech/tags/vision.md>), [vlm](<https://devfeed.tech/tags/vlm.md>)

## AI overview

SmolVLM2 introduces compact video-language models for video and visual understanding across devices. The article highlights three model sizes, MLX-ready Python and Swift APIs, and benchmark performance including Video-MME.

## Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.