09-14-2026, 11:14 AM
Interesting, I hadn't tried that. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
|
4090 vs 5090 for 70B quants on dual 3090
|
|
« Next Oldest | Next Newest »
|
Users browsing this thread: 2 Guest(s)