Feed efficiency is expensive to measure in beef cattle because of the technology it requires to measure individual animal dry matter intakes (DMI). One potential solution is to develop methods to effectively utilize pen feed intake data for genetic evaluation. Genetic correlations between predicted DMI (pDMI) and actual DMI reported in the literature indicate that pDMI may be useful as an indicator trait. Therefore, the objective of this study is to evaluate whether quantitative trait loci (QTL) mapping approaches identify the same regions of the genome for pDMI and DMI. Because average daily gain (ADG) is a primary driver of the prediction models, the overlap of pDMI and DMI QTL regions with QTL for ADG will also be evaluated. To achieve these objectives, individual animal feed intake, weight, and carcass data was obtained on 849 Hereford steers and heifers fed within a GrowSafe (GrowSafe Systems Ltd.) feed intake system. The Cattle Value Discovery System (CVDS) growth and carcass data model was utilized to obtain pDMI from DMI pooled within pens and reallocated to individual animals. Phenotypic correlations were 0.64 (P < 0.0001) and 0.56 (P < 0.001) between pDMI and DMI and pDMI and ADG, respectively. Genotypes were collected using the Illumina BovineHD Beadchip assay (Illumina Inc., San Diego, CA), and after data filtering, a final data set of 648,625 single nucleotide polymorphisms (SNP) were available for analysis. The SNP effects for ADG, pDMI, and DMI were estimated utilizing a BayesB0 model in GenSel. The 5-SNP windows surrounding the 100 largest SNP effects for each phenotype were compared with determine overlap between QTL regions. Concordance of QTL regions was 50% between pDMI and ADG, 26% between pDMI and DMI, and 19% between DMI and ADG. Seven of the QTL regions in common between pDMI and DMI were independent of ADG QTL regions. These results show that there is concordance between genomic regions for pDMI and DMI independent of the model drivers (ADG), and additional research will be conducted to characterize these regions of interest in genomic prediction for feed efficiency.