Model card: say what a smaller machine trades for fitting

Paging already said a machine that cannot hold the experts streams them. This says what that costs -- a wait on the SSD per token that routes to an expert not in memory -- without inventing a number we have not measured.

README.md

@@ -46,6 +46,14 @@ fills what fits and streams the rest from disk. On a 512 GB Mac Studio with room
 to spare this model settles at about **172 GB** resident. A smaller machine holds
 less and reads more from disk -- slower, but it runs.
 
+How much slower depends on how far the machine is from holding the experts, and
+on how fast its disk is. Each token routes to a few experts; the ones already in
+memory cost nothing to reach, and the ones that are not have to be read before
+that token can finish. A machine holding most of them waits rarely, one holding
+few waits often. We have not measured this across machine sizes and will not
+guess a figure: what we can say is that the model answers either way, and that
+the wait is the SSD's, not the model's.
+
 ## Install
 
 ```bash