15:00
2026-10-08
startupfortune.com
artificial-intelligence
Samsung's LittleBit squeezes AI models to a tenth of a bit per weight
Samsung Research's LittleBit quantization technique compresses Llama2-13B to under 0.9GB and Llama2-70B to under 2GB by binarizing low-rank latent factors to roughly 0.1 bits per weight, a nearly 31x …