We present a streaming algorithm for reconstructing closed surfaces from large non-uniform point sets based on a geometric convection technique. Assuming that the sample points are organized into slices stacked along one coordinate axis, a triangle mesh can be efficiently reconstructed in a streamable layout with a controlled memory footprint. Our algorithm associates a streaming 3D Delaunay triangulation data-structure with a multilayer version of the geometric convection algorithm. Our method can process millions of sample points at the rate of 50k points per minute with 350 MB of main memory.