Liquid AI releases LFM2.5 Q4_0 checkpoints distilled for quantization

Liquid AI released Q4_0 GGUF checkpoints for LFM2.5-230M, LFM2.5-350M, LFM2.5-1.2B-Instruct, and LFM2.5-2.6B on August 19, 2026. The company says quantization-aware distillation recovers 97% of the loss relative to BF16 and improves decoding throughput on edge hardware.

Visit original source