+- 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: dual GPU split inference with LM Studio (/showthread.php?tid=241)
dual GPU split inference with LM Studio - signaltrack44 - 09-12-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
This isn't revolutionary, but the combination of Ollama and dual 3090 felt surprisingly usable once I tuned around quant drift.
Maybe useful as a starting point for newer folks.
This is mostly for local work rather than public serving.
Re: dual GPU split inference with LM Studio - sparrowgrid - 09-14-2026
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Llama and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: dual GPU split inference with LM Studio - tensorfield88 - 09-15-2026
What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?
Re: dual GPU split inference with LM Studio - sanevault - 09-18-2026
That matches what I was seeing. I ended up in about the same place using MLX. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: dual GPU split inference with LM Studio - routeforge64 - 09-18-2026
A couple things I'd check first. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: dual GPU split inference with LM Studio - paperrunner - 09-19-2026
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.