Liquid AI trains 4-bit LFM2.5 checkpoints to retain roughly 97% of BF16 performance
The MIT spinout used quantization-aware distillation across four LFM2.5 models, then tested them on a phone, laptop, mini PC and Raspberry Pi.
By RuntimeWire Staff · Published

The MIT spinout used quantization-aware distillation across four LFM2.5 models, then tested them on a phone, laptop, mini PC and Raspberry Pi.