Image + textVisual document search

LensVLM

Reads long documents differently: it turns pages into downscaled images and expands the full text only for the pages needed to answer. A long document then costs far less context.

Developer
Apple, USA
First release
Sep 2026
Latest release
Sep 2026
Sizes
9B
License
Non-commercial onlyApple Machine Learning Research Model License: research only, commercial use is not granted. Fine-tuned from Qwen3.5-9B, whose terms also apply
Russian
Not stated
Running
On your own serverNeeds a GPU
Industries
Documents and accounting, Science and research, Legal
Deploy on your server Hugging Face

What it does

  • Answering questions over multi-page documents
  • Finding the right page in a large report or case file
  • Working with scans and PDFs without a separate OCR step
  • Research on long-context handling

Where it is used

Document workflowsResearch groupsLegal departments

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. LensVLM-9B

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can LensVLM be used in a commercial project?

No. License: Apple Machine Learning Research Model License: research only, commercial use is not granted. Fine-tuned from Qwen3.5-9B, whose terms also apply. A commercial product needs a different model or a separate agreement with the rights holder.

What hardware does LensVLM need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does LensVLM support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download LensVLM and what does it cost?

The LensVLM weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Visual document searchColPali / ColQwenIlluin Technology (ViDoRe team) · FranceCommercial use with conditions

Searches PDFs and scans as images: pages do not need to be OCR'd first, the model finds the right one for a question directly, including tables and charts. Trained on English.

DetailsImage + textQwen-VLAlibaba (Qwen team) · ChinaCommercial use allowed

One of the strongest open vision models: reads documents, tables, charts and video, and works with user interfaces. Since Qwen3.5, vision is built directly into the main Qwen model.

DetailsDocuments and OCRSmolDocling и Granite-DoclingIBM and Hugging Face · USACommercial use allowed

Tiny models for the open Docling document converter: they turn a page into markup with tables, formulas and code. Run on an ordinary laptop.

Details

Source: huggingface.co/apple/LensVLM-9B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.