Liquid AI Releases LFM2.5-VL-450M: a 450M-Parameter Vision-Language Model with Bounding Box Prediction, Multilingual Support, and Sub-250ms Edge Inference
450M parameters. Sub-250ms inference. Liquid AI's new vision-language model runs on edge hardware nobody thought could handle it.
Why it matters
Liquid AI's LFM2.5-VL-450M demonstrates that capable vision-language models no longer require cloud infrastructure—bounding box prediction, multilingual support, and function calling now fit in edge devices, reshaping deployment economics for enterprises building offline-first AI products.
The key facts
6 to knowModel: LFM2.5-VL-450M (450M parameters)
Inference latency: Sub-250ms on edge hardware
New capabilities: Bounding box prediction, improved instruction following, expanded multilingual understanding, function calling
Target hardware: NVIDIA Jetson Orin, mini-PCs, embedded AI modules
Model type: Vision-language model
Release date: April 11, 2026
Go to the source
MarkTechPostmarktechpost.com
Publisher excerpt: Liquid AI just released LFM2.5-VL-450M, an updated version of its earlier LFM2-VL-450M vision-language model. The new release introduces bounding box prediction, improved instruction following, expanded multilingual understanding, and function calling support — all within a 450M-parameter footprint…