Re:M5 Ultra Mac Studio Review: The Dream Mac for Local AI Ag...
by api on Monday September 21, 2026 @12:37PM
(#49789583)
I assume those are non-batched. I think the M series GPU can do 4X to 8X depending on model quant, which means if you can batch queries you'll get almost 4X to 8X performance.
[ Parent
| on HN ]
There are no comments on this comment yet.