LensVLM 9B

LensVLM 9B by apple, a image-text-to-text model with multimodal capabilities. Understand and compare multimodal features, benchmarks, and capabilities.

Comparison

Feature	LensVLM 9B	Interfaze
Input Modalities	text, image	image, text, audio, video, document
Native OCR	No	Yes
Long Document Processing	No	Yes
Language Support	unknown	162+
Native Speech-to-Text	No	Yes
Native Object Detection	No	Yes
Guardrail Controls	No	Yes
Context Input Size	32.8K	1M
Tool Calling	Yes	Tool calling supported + built in browser, code execution and web search

Scaling

Feature	LensVLM 9B	Interfaze
Scaling	Self-hosted/Provider-hosted with quantization	Unlimited

View model card on Hugging Face

LensVLM is a 9B Vision Language Model (VLM) that scans compressed images of text, then selectively expands only the relevant pages to their uncompressed form via learned tools.

License

All ML model files in this repository, including Apple's modifications to the Qwen model, are provided under the terms of the Apple Machine Learning Research Model License.

The source code that accompanies this model is distributed separately and is provided under the terms of the Apple Sample Code License.

Usage

Install the LensVLM code and run inference:

git clone https://github.com/apple-aiml-research/ml-lensvlm
cd ml-lensvlm
pip install -r requirements.txt
python scripts/run_demo.py --model apple/LensVLM-9B

For a custom document:

python demo.py \
    --model apple/LensVLM-9B \
    --text_file document.txt \
    --question "What is the main finding?" \
    --compression 10x

Compression options: 5x, 10x, 15x. See the repository README for data preparation and evaluation.

Citation

@article{xie2026lensvlm,
  title={LensVLM: Selective Context Expansion for Compressed Visual Representation of Text},
  author={Xie, Roy and Friedman, Dan and Yu, Donghan and Pan, Bowen and Fifty, Christopher and Kim, Jang-Hyun and Du, Xianzhi and Gan, Zhe and Rathod, Vivek and Dhingra, Bhuwan},
  journal={arXiv preprint arXiv:2605.07019},
  year={2026}
}