Hugging Face Vision Models

Compare both Hugging Face vision models we track, all of them open-weight.

2 models · 2 open-weight · Updated Feb 2025

About Hugging Face Vision Models

Every Hugging Face vision model in our catalog is open-weight. Both publish downloadable weights, so you can self-host under their own licenses instead of paying per request. The open-weight side runs on Apache 2.0 and MIT licenses. The newest additions are SmolVLM2 (Feb 2025) and YOLOS (Jun 2021).

Between them, the Hugging Face models we list cover 4 distinct vision tasks. They cover captioning (1 model), object detection (1), and vision language (1).

On the open-weight tier, SmolVLM2 runs at 256M – 2.2B parameters. Both carry a permissive license, so commercial use is straightforward.

With every model here open-weight, the real trade is size against generality: the smaller checkpoints fine-tune and deploy cheaply on your own hardware, while the larger ones cover more ground out of the box. Compare their licenses, sizes, prices, and release dates in the tables below, then open any model page for the full specification.

Which Hugging Face Model Should You Use?

What each of the 2 Hugging Face vision models in our catalog is built for, and how you run it.

SmolVLM2: Best for: Captioning and Visual Question Answering. Open weights: Apache 2.0 license, 256M – 2.2B parameters. Self-host it or run it here. Small enough for on-device and edge deployment.
YOLOS: Best for: Object Detection. Open weights: MIT license. Self-host it or run it here.

Open-Source Hugging Face Models

2 models with downloadable weights you can self-host under their licenses (Apache 2.0 and MIT).

SmolVLM2

SmolVLM2 is a compact multimodal vision-language model developed by the Hugging Face TB Research team, released in February 2025 under the Apache 2.0 license. It is designed for efficient image and video understanding on resource-constrained hardware, with model variants ranging from 256M to 2.2B parameters. SmolVLM2 processes images, multi-image inputs, and video alongside text queries to generate text outputs for tasks including visual question answering, image captioning, and OCR.SmolVLM2 is designed for on-device and edge deployment, requiring substantially less GPU memory than comparable multimodal models. It supports standard fine-tuning pipelines via the Hugging Face transformers library and quantization through bitsandbytes. SmolVLM2 is suited for applications where a capable vision-language model is needed without full server-scale infrastructure.

YOLOS

YOLOS (You Only Look at One Sequence) is a transformer-based object detection model widely distributed through Hugging Face Transformers, released in June 2021 under the MIT license. It applies a minimally adapted Vision Transformer to object detection by representing both the image and detection tokens as a flat sequence processed by standard multi-head self-attention, without convolutional components or feature pyramid networks. The architecture demonstrates that detection can be performed without region proposals or multi-scale feature fusion.YOLOS achieves moderate performance on COCO relative to purpose-built detectors, with its primary contribution being a demonstration of the transferability of ViT pre-training to detection tasks. It is most appropriate for research contexts exploring transformer-based detection architectures and for scenarios where architectural simplicity is preferred over peak accuracy.

Frequently Asked Questions About Hugging Face Vision Models

Which Hugging Face models can do captioning?

1 of the 2 Hugging Face vision models we track handles captioning: SmolVLM2. Each model page lists its full task coverage, license, and specs.

Which Hugging Face models can do object detection?

1 of the 2 Hugging Face vision models we track handles object detection: YOLOS. Each model page lists its full task coverage, license, and specs.

Are Hugging Face vision models open source?

Yes. Both Hugging Face vision models we track publish downloadable weights you can self-host under their licenses (Apache 2.0 and MIT).

How many Hugging Face vision models are on Roboflow Playground?

We track 2 live Hugging Face vision models. The most recent addition is SmolVLM2, released Feb 2025.

This page lists both Hugging Face vision models in the Roboflow Playground catalog, all of them open-weight and free to self-host. They cover captioning, object detection, and vision language, among other tasks. Compare licenses, parameters, prices, and release dates side by side, or open any model page for full details.