+- 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: Used A6000 worth it now (/showthread.php?tid=708)
Pages:
1
2
Re: Used A6000 worth it now - batchwire - 10-09-2026
Can you fill in a bit more context? Are you testing this on M3 Max or something else?
Re: Used A6000 worth it now - cozywire - 10-09-2026
What worked for me was pretty simple. On 4090, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: Used A6000 worth it now - cudapoint - 10-09-2026
Not sure I agree there. I get why that seems right, but on M3 Max the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Re: Used A6000 worth it now - dockkite69 - 10-09-2026
Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.