EVERY SIGNAL, SORTED.

Liquid AI, LFM3, Small Language Models, Multimodal AI, Edge Computing, Open Weights, Quantization, On-Device AI, Vision, Audio, Decision Models, Performance Testing and Software Licensing

Liquid AI put six small multimodal models on one backbone. Test the edge claim

LFM3 branches one compact base into text, vision, audio, omni and decision models. The useful promise is local specialization. The proof still has to happen on the exact device, runtime and workload that will ship.