Use GaLore, not LoRA, when you actually need full-parameter fine-tuning on one consumer GPU

Future AGI·medium signal

LoRA freezes the base weights and only learns small adapter matrices; GaLore instead projects the full gradients into a low-rank subspace, which enables genuine full-parameter training of a 70B model on consumer-grade hardware. For builders whose task needs the base weights to move (not just an adapter grafted on) but who can't afford a datacenter, this is the technique that changes what's feasible at home. It's a different point on the memory/quality trade-off than the LoRA/QLoRA default most tutorials still push.