LFM3-VL-2B
LFM3-VL-2B is a 1.92B vision-language model built on the LFM3 text backbone.
What the release provides
The checkpoint combines a 164M vision encoder and 25M projector with the language model. It accepts text, images and video, supports thinking, and has a shared 128K context.LFM3-VL-2B official model card
How to use it well
Practical guidance. Review OCR, object positions and video questions separately. Keep the frame sampling and image preparation fixed during comparisons. A useful answer about an image still needs a stable coordinate contract before it can control an application.
Hosted API contract
The API catalog lists lfm3-vl-2b with a 128,000-token window. Its supported inputs and limits can differ from the downloadable checkpoint.Liquid API model catalog
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API, Downloadable |
| Model identifiers | LiquidAI/LFM3-VL-2Blfm3-vl-2b |
| Context window | 131,072 tokens Downloadable checkpoint limit; the hosted API has a separate service contract. LFM3-VL-2B official model card |