Ultra-Quiet Computing for Deep Learning Researchers Designed for deep learning research, this WhisperStation features a high-speed 6-core Xeon Broadwell processor, 64GB DDR4 memory, four NVIDIA TITAN Xp GPUs, an SSD for the operating system, 6TB of high-speed RAID10 storage (with SSD caching, if desired) and ultra-quiet fans. We provide a turn-key system delivered with Ubuntu Linux, NVIDIA CUDA, NVIDIA cuDNN and your choice of machine learning software pre-installed (e.g., TensorFlow, Caffe, Torch, Theano, NVIDIA cuDNN, NVIDIA DIGITS). The WhisperStation-Deep Learning workstation is a commercially-available system based upon NVIDIAs DIGITS DevBox. It has been designed to provide maximum performance when training deep neural networks. It is the perfect system for a researcher exploring the applications of machine learning before such applications move into production. Using NVIDIAs DIGITS interface for popular deep learning tools, such as Caffe, researchers can collaborate and share GPU resources as they fine-tune their neural networks. For production-level deep learning, we recommend our professional NumberSmasher server product line with NVIDIA Tesla GPUs.