如何最小化类“lm”对象的大小而不影响它传递给predict（）

I want to run lm() on a large dataset with 50M+ observations with 2 predictors. The analysis is run on a remote server with only 10GB for storing the data. I have tested ´lm()´ on 10K observations sampled from the data and the resulting object had size 2GB+. on a large dataset with 50M+