LFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation
Liquid AI released Quantization-Aware Distillation (QAD) Q4_0 GGUF checkpoints for four LFM2.5 models that retain about 96.5%–97.4% of BF16 baseline accuracy lost to quantization (97.1% for 230M, 96.5% for 350M, 97.4% for 1.2B-Instruct, 96.6% for 2.6B).
Aug 19, 2026 ·Hugging Face



















