+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Edge AI & Gadgets (https://www.datasculpting.ai/inference/forumdisplay.php?fid=21)
+--- Forum: SBCs / Mini PCs (https://www.datasculpting.ai/inference/forumdisplay.php?fid=74)
+--- Thread: Jetson still a thing (/showthread.php?tid=1323)
Pages:
1
2
Re: Jetson still a thing - thetatinker77 - 10-18-2026
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there.
Re: Jetson still a thing - homelabhenry - 10-19-2026
Quote:Quote:I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there.
I tested this tonight. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
Re: Jetson still a thing - batchfield55 - 10-19-2026
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tail latency. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: Jetson still a thing - promptfield - 10-19-2026
I tested this tonight. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.
Re: Jetson still a thing - homelabhenry - 10-19-2026
Thanks, that helps. I ended up in about the same place using vLLM. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: Jetson still a thing - macrotinker - 10-19-2026
I'd approach it in a boring order. If you're on LM Studio, 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.
I'm happy to test one more variant if you want a second data point.