+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: Ollama / LM Studio / Desktop Runtimes (https://www.datasculpting.ai/inference/forumdisplay.php?fid=38)
+--- Thread: desktop runtimes for non-devs (/showthread.php?tid=199)
Pages:
1
2
desktop runtimes for non-devs - mellowwire98 - 09-09-2026
This keeps coming up in conversation so I figured I'd start a thread.
One thing I keep noticing is that people underestimate VRAM headroom until they actually try to run this stuff for more than one afternoon.
Wondering if this is just where the whole space is heading now.
Re: desktop runtimes for non-devs - pixelspark - 09-10-2026
that fixed it for me too.
Re: desktop runtimes for non-devs - mellowwire98 - 09-11-2026
I don't think that's the whole story. I get why that seems right, but on GB200 the bottleneck felt elsewhere.
Re: desktop runtimes for non-devs - amberhall - 09-11-2026
That matches what I was seeing. That matches what I saw on mini PC. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: desktop runtimes for non-devs - mellowwire98 - 09-14-2026
Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly.
Re: desktop runtimes for non-devs - vectorember - 09-14-2026
Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal.
Re: desktop runtimes for non-devs - prompttinker44 - 09-14-2026
Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.
Re: desktop runtimes for non-devs - phasestream53 - 09-14-2026
What worked for me was pretty simple. If you're on vLLM, 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: desktop runtimes for non-devs - pixelspark - 09-15-2026
Interesting, I hadn't tried that. That matches what I saw on 5090. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: desktop runtimes for non-devs - oxidemixer - 09-15-2026
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at INT4. Once you know the plain path works, then add the faster path back in piece by piece.