+- 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: RTX 5090 local inference: anyone testing this? (/showthread.php?tid=197)
Pages:
1
2
Re: RTX 5090 local inference: anyone testing this? - turboyard94 - 09-19-2026
I'd approach it in a boring order. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
Re: RTX 5090 local inference: anyone testing this? - amberhall - 09-20-2026
I tested this tonight. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.