+- 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 on A6000 (/showthread.php?tid=493)
Pages:
1
2
Re: QLoRA resource reality check on A6000 - batchpeak - 10-02-2026
Need a little more detail here. What model, what runtime, and roughly what context size?
Re: QLoRA resource reality check on A6000 - routearch - 10-05-2026
Good point. I ended up in about the same place using LM Studio. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: QLoRA resource reality check on A6000 - kernelghost - 10-05-2026
Quote:Good point. I ended up in about the same place using LM Studio. The biggest change for me was simplifying the stack instead of adding one more optimiz
Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.