+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Hardware (https://www.datasculpting.ai/inference/forumdisplay.php?fid=4)
+--- Forum: GPUs (https://www.datasculpting.ai/inference/forumdisplay.php?fid=28)
+--- Thread: 4090 vs 5090 for 70B quants on dual 3090 (/showthread.php?tid=136)
Pages:
1
2
Re: 4090 vs 5090 for 70B quants on dual 3090 - paperrunner - 09-14-2026
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?
Re: 4090 vs 5090 for 70B quants on dual 3090 - rocmriley - 09-14-2026
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.
Re: 4090 vs 5090 for 70B quants on dual 3090 - signaltrack44 - 09-14-2026
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.
Re: 4090 vs 5090 for 70B quants on dual 3090 - cozysmith - 09-15-2026
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.
Re: 4090 vs 5090 for 70B quants on dual 3090 - amberhall - 09-18-2026
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.
Re: 4090 vs 5090 for 70B quants on dual 3090 - signaltrack44 - 09-20-2026
that fixed it for me too.