Best Image Tagging Models

Image tagging is the task of assigning multiple descriptive keywords to an image, such as "beach", "sunset", and "people", rather than forcing a single category. Technically it is multi-label prediction: the model scores each candidate tag independently (a sigmoid per tag instead of one softmax), and CLIP-style embedding models can tag against an open vocabulary by matching the image to arbitrary tag texts. Precision and recall are evaluated per tag because a photo legitimately carries many. Tagging feeds digital asset management, photo library search, e-commerce attribute enrichment, and metadata generation at scale. This page lists 63 image tagging models, including 24 open-weight options you can self-host; 61 of them run live in the Playground so you can test them on your own images.

It depends on your task and constraints. For fixed categories in production, a model fine-tuned on your own data typically beats any general-purpose model. Compare the image tagging models on this page and try them on your own image to see which fits.

Yes. 24 of the 63 image tagging models here are open-weight (for example Kimi K3, Qwen3.6 27B, and Qwen3.6 35B A3B), free to self-host under their licenses (Modified MIT, Apache 2.0, and Custom).

Yes. You can run 61 of them in the Roboflow Playground for free. Upload an image and compare the models' output side by side, no setup required.