+- 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: Hosted (https://www.datasculpting.ai/inference/forumdisplay.php?fid=50)
+---- Thread: best setup on 24GB VRAM: early impressions (/showthread.php?tid=540)
Pages:
1
2
best setup on 24GB VRAM: early impressions - deepseeked - 09-27-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
This isn't revolutionary, but the combination of SGLang and A6000 felt surprisingly usable once I tuned around tool calling.
If someone wants the exact settings I can clean them up and post them.
Re: best setup on 24GB VRAM: early impressions - fastquill74 - 09-29-2026
What exact setup are you running? What model, what runtime, and roughly what context size?
I'm happy to test one more variant if you want a second data point.
Re: best setup on 24GB VRAM: early impressions - deepseeked - 09-30-2026
I hit almost the same issue last night.
Re: best setup on 24GB VRAM: early impressions - northcraft90 - 10-01-2026
Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed.
Re: best setup on 24GB VRAM: early impressions - promptfield - 10-01-2026
A couple questions before I guess too hard. What model, what runtime, and roughly what context size? Turns out 'just one more test' was a lie.
Re: best setup on 24GB VRAM: early impressions - latentcraft - 10-01-2026
That matches what I was seeing. The pattern around speculative decoding has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: best setup on 24GB VRAM: early impressions - macropilot - 10-01-2026
I'd start with the simpler stack.
Re: best setup on 24GB VRAM: early impressions - deepseeked - 10-01-2026
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there.
Re: best setup on 24GB VRAM: early impressions - embershed99 - 10-01-2026
What exact setup are you running? Is this local-only or are you routing anything externally?
Re: best setup on 24GB VRAM: early impressions - macrolab - 10-01-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.