Liquid AI Releases LFM2.5-Encoder-230M and LFM2.5-Encoder-350M: Bidirectional Encoders That Stay Fast at 8K Context on CPU

Liquid AI has released two open-weight bidirectional encoders, LFM2.5-Encoder-230M and LFM2.5-Encoder-350M, which utilize the company's hybrid LFM2 architecture. These models maintain performance at an 8,192-token context length while remaining optimized for efficient operation on CPUs.