Cloudflare's clef-flash multimodal model trends on Hugging Face

Cloudflare · hf · 2026-10-02

Cloudflare's clef-flash model is trending on Hugging Face. Built on the Qwen3.5 architecture, it's an image-text-to-text model whose tags point to a distinctive post-training focus: image-text-to-typed-output, i.e., producing structured, typed output from image and text inputs.

Related event: Cloudflare Open-Sources Its First Models clef and clef-flash, Topping the Jev Decision Index(23 posts)→

Original post →

More from Models

Models channel →