Liquid AILFM2.5
LFM2.5-VL-1.6B
LFM2.5-VL-1.6B is a smaller text-and-image checkpoint built on the LFM2.5-1.2B base.
What the release provides
The model supports multiple images, OCR and multilingual visual questions within a 32,768-token context.LFM2.5-VL-1.6B official model card
How to use it well
Practical guidance. Compare document and photo tasks separately. Check whether image resizing removes details the question needs. For a local assistant, measure how image processing affects response time and memory alongside ordinary text chat.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | LiquidAI/LFM2.5-VL-1.6B |
| Context window | 32,768 tokens Downloadable checkpoint limit; the hosted API has a separate service contract. LFM2.5-VL-1.6B official model card |