Ocean heat uptake (OHU) plays an important role in determining the rate of surface warming under CO2 forcing. We examined the transient response to CO2 forcing in a set of 30 climate models from Coupled Model Intercomparison Project Phase 6 (CMIP6) and found that the intermodel spread in OHU efficiency largely depends on the base-state ocean stratification, especially in the Southern Ocean. This dependence is primarily traced to ocean salinity rather than ocean temperature. Models with weaker ocean stratification primarily due to higher upper-ocean salinity tend to sequester heat into the deeper ocean, leading to a lower rate of surface warming, a primary reason for higher OHU efficiency; the stratification impact on total OHU is secondary. We applied the relationship between salinity and OHU efficiency for an emergent constraint on OHU efficiency, suggesting an OHU efficiency higher than the CMIP6 multimodel average and arguing against models with extremely low efficiency. Plain Language Summary Over 90% of the anthropogenic heat due to increased greenhouse gas emissions is stored in the ocean through the so-called ocean heat uptake (OHU) process. How fast the land and ocean surfaces are warming to a large extent depends on how fast the heat is absorbed into the ocean. The OHU efficiency, defined to describe the ratio of global OHU change to global surface warming, shows a considerable spread among Coupled Model Intercomparison Project Phase 6 (CMIP6) climate models. This spread largely depends on the models' difference in preconditioning ocean stratification as over most ocean weaker stratification indicates more conducive sea waters for OHU. Models' spread in ocean stratification is primarily attributed to ocean salinity—especially in the upper oceans—rather than ocean temperature. Models with higher base-state upper-ocean salinity tend to sequester heat into the deeper ocean and thus produce less surface warming, the primary cause of higher OHU efficiency. The physical relationship between ocean salinity and OHU efficiency can be further applied to statistically constrain the latter using the observational salinity data sets. The constraint tends to narrow the uncertainty in OHU efficiency among models and argue that low efficiency models are less realistic.