Apple publishes LensVLM-9B, a research vision-language model that reads compressed images of text

In September 2026 Apple published LensVLM-9B on Hugging Face, a 9B vision-language model that scans compressed images of text and selectively expands only the relevant pages to their uncompressed form through learned tools. The model card lists Qwen3.5-9B as the base model and says the model files, including Apple's modifications to the Qwen model, are provided under the Apple Machine Learning Research Model License, while the accompanying code in the apple-aiml-research/ml-lensvlm repository is under the Apple Sample Code License. The model accompanies the paper "LensVLM: Selective Context Expansion for Compressed Visual Representation of Text." USASI has not tested LensVLM-9B.12

USASI. (2026, October 13). Apple publishes LensVLM-9B, a research vision-language model that reads compressed images of text. United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/news/apple-releases-lensvlm-9b/

@misc{usasi_news_apple_releases_lensvlm_9b,
  author = {{USASI}},
  title = {Apple publishes LensVLM-9B, a research vision-language model that reads compressed images of text},
  year = {2026},
  month = oct,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/news/apple-releases-lensvlm-9b/}},
  note = {United States of America Superintelligence. Last updated 2026-10-13}
}