+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: LLM Models (https://www.datasculpting.ai/inference/forumdisplay.php?fid=12)
+--- Forum: Open Weight (https://www.datasculpting.ai/inference/forumdisplay.php?fid=49)
+---- Forum: Recipes & Configurations (https://www.datasculpting.ai/inference/forumdisplay.php?fid=52)
+---- Thread: routing between local and hosted: what are you seeing? (/showthread.php?tid=1204)
routing between local and hosted: what are you seeing? - cobaltworks25 - 10-14-2026
Has anyone else run into this?
My current setup is TensorRT-LLM with Threadripper box, and I keep running into VRAM headroom.
Not looking for the perfect answer, mostly what worked in real use.
I expected the biggest difference to come from the model, but the stack around it mattered at least as much.
Re: routing between local and hosted: what are you seeing? - northgrid33 - 10-14-2026
Good point. The pattern around structured output has been pretty similar for me.
Re: routing between local and hosted: what are you seeing? - sparrowkite53 - 10-16-2026
Interesting, I hadn't tried that. That matches what I saw on 5090.
Re: routing between local and hosted: what are you seeing? - signalpeak - 10-16-2026
Interesting, I hadn't tried that. I ended up in about the same place using TensorRT-LLM. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
If you post your exact settings, people here can probably narrow it down pretty fast.
Re: routing between local and hosted: what are you seeing? - northhall88 - 10-17-2026
Not sure I agree there. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.
Re: routing between local and hosted: what are you seeing? - turboscope5 - 10-17-2026
What worked for me was pretty simple. If you're on TensorRT-LLM, 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: routing between local and hosted: what are you seeing? - edgequill - 10-18-2026
My first guess would be this: On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: routing between local and hosted: what are you seeing? - circuitkite - 10-18-2026
Need a little more detail here. Is this local-only or are you routing anything externally?
Re: routing between local and hosted: what are you seeing? - cudahouse - 10-19-2026
Quote:Need a little more detail here. Is this local-only or are you routing anything externally?
A couple things I'd check first. If you're on PyTorch, 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.