Our objective was to model dry matter intake (DMI) in mid-lactation Holstein dairy cows based on milk energy (MilkE), energy required for maintenance, change in body weight (ΔBW), body condition score (BCS, scale 1 to 5), height (Ht), days in milk (DIM), and parity. The database contained weekly DMI of 4,031 lactations from 3,393 Holstein cows from research stations across the US. The average and standard deviation of all variables were 25 ± 4 kg DMI, 30 ± 6 Mcal/d MilkE, 125 ± 12 kg^0.75 BW^0.75, 630 ± 80 kg BW, 124 ± 12 kg^0.75 BWBCS3^0.75, 620 ± 80 kg BWBCS3, 0.36 ± 1.29 kg/d ΔBW, 3.0 ± 0.4 BCS, 114 ± 37 DIM, and 149 ± 6 cm Ht, where BWBCS3 is the BW adjusted to a BCS of 3. Four full models were generated to model DMI wherein each model contained 1 of the 4 ways of expressing BW shown above. The full models contained fixed effects of the covariates described previously, parity, and all possible 2-way interactions between parity and the other covariates. Cow, diet, experiment, and location were included as random effects. The full models were first subjected to forward selection. The resulting models were then analyzed using HPMIXED from SAS 9.4, where the non-significant covariates (P > 0.05) were removed. In this process the effects of parity, height, and change in BW were removed in all models. The final models were compared based on the root mean square error of prediction (RMSEP), decomposition MSEP, mean bias, and concordance correlation coefficient (CCC). The suggested model is: DMI (kg/d) = 2.62 + 0.326 × MilkE (Mcal/d) + 0.0243 × BW (kg) − 0.89 × BCS (RMSEP = 2.59 kg, Mean bias, %MSEP = 0.001, Slope bias, %MSEP = 0.001, Mean bias = −0.001 kg, and CCC = 0.78). The selected model has smaller mean bias and higher CCC than the equation suggested by NRC (2001, Mean bias = −2.33, CCC = 0.57) to predict DMI and has potential to benefit nutritionists during diet formulation. To apply this equation for early-lactation cows it is necessary to use an adjustment factor for DIM.