Yep that's what I was going to do... train in 2 steps and merge. But, I think the spawning idea would still work as well. My understanding is that 32-bit applications are limited to mem usage of 1.5-2.0 gig (mine crashed around 1.5, and that is also what I read some other people were saying)

The limitation, as I understand, is per-application. If you could somehow spawn the training into multiple Zorros then you could circumvent that limit. The VM itself has 4 gigs available.

PS: thanks for the tip on the Combine script... I'll definitely check that out.