+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: AMD / ROCm (https://www.datasculpting.ai/inference/forumdisplay.php?fid=32)
+--- Thread: is RDNA worth the hassle yet: worth it? (/showthread.php?tid=117)
is RDNA worth the hassle yet: worth it? - relaynest82 - 09-03-2026
Did a bit of testing and thought I'd post the result here.
After a few runs on GB200, I ended up with decent performance, but the setup only really made sense once I adjusted around quant drift.
Curious if anyone else landed in the same place.
My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
Re: is RDNA worth the hassle yet: worth it? - fastquill74 - 09-04-2026
Can you fill in a bit more context? What model, what runtime, and roughly what context size?