Mathias Lechner

Liquid AI released an experimental 279.5-million-parameter draft model, DSpark, for its LFM2.5-VL-3B vision-language model on September 24th, which the company says cuts decoding time by up to 3.13x o…

Liquid AI, an MIT spinout, released four updated LFM2.5 checkpoints on August 19, trained with quantization-aware distillation (QAD) to retain roughly 97% of their BF16 average benchmark performance w…

Liquid AI released its LFM2.5-230M foundation model on June 25, outperforming larger competitors like Alibaba's Qwen3.5-0.8B and Google's Gemma 3 1B on data extraction benchmarks. The 230-million-para…