+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Optimization & Performance (https://www.datasculpting.ai/inference/forumdisplay.php?fid=10)
+--- Forum: Benchmarks (https://www.datasculpting.ai/inference/forumdisplay.php?fid=43)
+--- Thread: QLoRA resource reality check with LM Studio (/showthread.php?tid=1110)
Pages:
1
2
Re: QLoRA resource reality check with LM Studio - cacheline - 10-17-2026
Quote:[quote]Thanks, that helps. The pattern around continuous batching has been pretty similar for me. I got better results once I stopped chasing one metr
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at prefill/decode split. Not glamorous advice, but repeatable baselines save a lot of time.
Re: QLoRA resource reality check with LM Studio - deltastation - 10-17-2026
Appreciate the detail. The pattern around batch size has been pretty similar for me.
Re: QLoRA resource reality check with LM Studio - quiethouse - 10-17-2026
Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.