+- 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 on mini PC (/showthread.php?tid=307)
Pages:
1
2
Re: RTX 5090 local inference on mini PC - signaltrack44 - 09-21-2026
What exact setup are you running? Are you testing this on mini PC or something else?
Re: RTX 5090 local inference on mini PC - mlxgarden - 09-21-2026
Quote:What exact setup are you running? Are you testing this on mini PC or something else?
My first guess would be this: On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: RTX 5090 local inference on mini PC - turboyard94 - 09-23-2026
That matches what I was seeing. I ended up in about the same place using Ollama. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.