Apple drops new HF model: Qwen3.5-9B finetune that turns long docs into page images to save tokens

yoobinray · x · 2026-09-25

Apple quietly released a new open model on Hugging Face: a Qwen3.5-9B finetune that compresses long documents into small page images to save tokens, then retrieves the full text of only the pages relevant to the user's question. The hybrid visual-compression approach aims to cut long-context processing costs while keeping access to exact original text.

Related event: Apple Open-Sources LensVLM-9B, a VLM That Reads Long Documents Like Flipping a Book(5 posts)→

Original post →

More from Models

Models channel →