Author summary Modern experimental techniques such as mass cytometry (CyTOF) make it possible to quickly make high-dimensional measurements on upwards of tens of millions of cells with single-cell resolution. An important problem in biology is to use these measurements to group together similar cells to identify biologically meaningful cell types that can be used to study disease progression, drug responses, and other clinical outcomes. However, the size and complexity of experimental data sets makes this problem computationally and theoretically extremely difficult. Here, we present a new algorithm HAL-X that accurately and quickly identifies cell clusters from biological data. Importantly, our algorithm does not require large amounts of memory. This eliminates the need for specialized high-end computing resources, allowing biologists to quickly analyze their data using a standard laptop or desktop computer.