Actually... you do not need that fast a network. You can converge state incrementally rather than transfer it in one go. Xen and VMware do this. Surely the cost of a fast SAN and interconnect would quickly outpace the (imho minor) savings from smaller memory allocations.
If you had all of the instance data stored on a fast SAN, so that it was available to all of the hosts simultaneously (possible.)
And you had an ultra-high speed interconnect (40Gbit Infiniband would do) between hosts, for sharing the memory state when you migrate..
4GB of memory, at 40Gbit/s would be transferred in 0.8s. (assuming perfect throughput, all cows are spherical, etc..)