Fire-induced indoor environments, characterized by smoke, glare, and dimness, critically challenge rescue safety. While LiDAR and cameras suffer from signal attenuation, millimeter-wave (mmWave) radar exhibits robust imaging performance. Radar-based building mapping and object detection in indoor environments are thus required to facilitate situational awareness specified by firefighting standards. Prior radar datasets mostly focus on outdoor object detection and the few existing indoor datasets remain insufficient in several aspects: (1) lacking adverse scenario analysis; (2) lacking raw analog-to-digital converter (ADC) data for dense point cloud generation; and (3) lacking 3D object annotations for building layout understanding. This work introduces the Indoor FireRescue Radar (IFR) dataset, a novel large-scale multimodal benchmark for indoor situational awareness. It includes 27K frames of 4D radar point cloud, co-calibrated with LiDAR, RGB camera, and IMU streams, alongside 3D objects annotations across 10 buildings. This dataset also provides raw ADC data and sensor configuration metadata. We applied voxel-based and pillar-based object detectors to 4D radar-based indoor object detection. We also demonstrated the robustness of radar perception in fire-induced indoor environments by real smoke tests at a firefighter training facility. Dataset is available at: https://huggingface.co/datasets/yysd123/indoor_mmwave