Apple Open-Sources LensVLM-9B, a Qwen3.5-9B Finetune That Shrinks Long Docs into Page Images

victormustar · x · 2026-09-24

Apple quietly released LensVLM-9B on Hugging Face, a finetune of Qwen3.5-9B that turns long documents into small page images to save tokens, then retrieves the full text of only the pages relevant to a user's question.

The page-image retrieval approach offers a novel token-efficient path for long-document understanding, and the model is open for download.

Related event: Apple Open-Sources LensVLM-9B to Save Tokens via Compressed Document Images(2 posts)→

Original post →

More from Models

Models channel →