High-performance image-classification model with 7,673,585 monthly downloads
Vit Base Patch16 224 (google/vit-base-patch16-224) is an industry-leading open-weights model hosted on Hugging Face. Supporting state-of-the-art inference across modern AI workloads.
Explore popular competitors and compare feature sets side-by-side.
High-performance text-to-image model with 256 monthly downloads
High-performance image-text-to-text model with 820,928 monthly downloads
Google's multimodal powerhouse with massive 1M-2M context window