09-08-2026, 11:55 AM
Maybe, but I had the opposite result. I get why that seems right, but on GB200 the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
|
4090 vs 5090 for 70B quants on dual 3090
|
|
« Next Oldest | Next Newest »
|