I built a video detective that runs on a 2B model and never phones home

Liquid AI shipped six open-weight models in the LFM3 family. Every one of them is derived from the same LFM3-1.7B base: a vision model, an omni model, an audio model, a text model, and their quantized variants. The launch coverage was benchmarks, which is the least interesting part of any model release. So I ignored the benchmarks and asked the only question that matters: what can I build with thi