Liquid AI Introduces LFM2.5-Embedding-350M and LFM2.5-ColBERT-350M: Dense Bi-Encoder and Late-Interaction Models for Fast Multilingual Search Across 11 Languages

Liquid AI has released two new 350-million parameter models designed to improve multilingual search capabilities on resource-constrained edge devices. By combining dense bi-encoder and late-interaction architectures, these tools allow for efficient information retrieval across 11 languages without requiring cloud-based processing.