+- 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 5090 (/showthread.php?tid=196)
RTX 5090 local inference on 5090 - rocmriley - 09-09-2026
Spent some time on this today and wanted to compare notes.
Two paths both seem viable, but they break down differently once prefill/decode split becomes important.
Trying to avoid rebuilding the whole thing twice.
My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
Re: RTX 5090 local inference on 5090 - batchwire - 09-11-2026
Interesting, I hadn't tried that. That matches what I saw on M3 Max.
Re: RTX 5090 local inference on 5090 - paperrunner - 09-11-2026
Quote:Interesting, I hadn't tried that. That matches what I saw on M3 Max.
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: RTX 5090 local inference on 5090 - visionforge - 09-12-2026
I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed.
Re: RTX 5090 local inference on 5090 - rocmriley - 09-15-2026
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
Re: RTX 5090 local inference on 5090 - torchshed - 09-18-2026
Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed.
Re: RTX 5090 local inference on 5090 - rocmriley - 09-18-2026
Thanks, that helps. That matches what I saw on mini PC. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: RTX 5090 local inference on 5090 - turbogrid11 - 09-18-2026
that fixed it for me too.
Re: RTX 5090 local inference on 5090 - sanevault - 09-18-2026
What worked for me was pretty simple. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: RTX 5090 local inference on 5090 - vrambandit - 09-19-2026
A couple things I'd check first. On A6000, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time. The logs were somehow calmer than I was.