Apple launched two new open models: FastVLM and MobileCLIP2

The models are up to 85x faster and 3.4x smaller than previous work

Suitable for high-res image processing tasks like OCR, image captioning, visual question answering, and image understandingpic.twitter.com/uG9ObsWACu

— The Rundown AI (@TheRundownAI) 2 septembre 2025

Apple launched two new open models: FastVLM and MobileCLIP2 The models are up to 85x faster and 3.4x smaller than previous work Suitable for high-res image processing tasks like OCR, image captioning, visual question answering, and image understanding

→ View original post on X — @therundownai