10-14-2026, 01:01 AM
Ran a quick check on my box. On 4090 with SGLang, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed.
small models can still be good
|
Apple unified memory limits: setup advice
|
|
« Next Oldest | Next Newest »
|
Users browsing this thread: 1 Guest(s)