09-14-2026, 02:16 AM
Quote:I tested this tonight. My result was mixed: first run looked bad, second run looked normal.
What exact setup are you running? Is this local-only or are you routing anything externally?
|
4090 vs 5090 for 70B quants on dual 3090
|
|
09-14-2026, 02:16 AM
Quote:I tested this tonight. My result was mixed: first run looked bad, second run looked normal. What exact setup are you running? Is this local-only or are you routing anything externally?
09-14-2026, 10:26 AM
That matches what I was seeing. 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.
7900 XTX / ROCm / somehow still optimistic
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.
09-15-2026, 11:15 PM
I'd approach it in a boring order. On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives.
09-18-2026, 11:52 PM
My first guess would be this: On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
09-20-2026, 11:58 AM
that fixed it for me too.
|
|
« Next Oldest | Next Newest »
|