+- 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 (/showthread.php?tid=1348)
best setup on 24GB VRAM - fastbench - 10-17-2026
Spent some time on this today and wanted to compare notes.
I've gone back and forth between llama.cpp and MLX for Qwen. The interesting difference for me has been HBM constraints.
What would you pick if you had to live with it for a few months?
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Re: best setup on 24GB VRAM - macrostack69 - 10-17-2026
That matches what I was seeing. I ended up in about the same place using vLLM. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: best setup on 24GB VRAM - macronest - 10-17-2026
Appreciate the detail. I ended up in about the same place using LM Studio. 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 - bytelab - 10-17-2026
I'd approach it in a boring order. On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.
Re: best setup on 24GB VRAM - cacheplane98 - 10-17-2026
My first guess would be this: On 7900 XTX, the easiest win is often to back off the aggressive settings and see whether the problem survives. Turns out 'just one more test' was a lie.
Re: best setup on 24GB VRAM - modrunner27 - 10-17-2026
Quote:My first guess would be this: On 7900 XTX, the easiest win is often to back off the aggressive settings and see whether the problem survives. Turns ou
Good point. That matches what I saw on Threadripper box. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: best setup on 24GB VRAM - cudaworks - 10-18-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: best setup on 24GB VRAM - deepseeked - 10-18-2026
Quote:What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there. A lot of these thread
Tried to reproduce it just now. On 4090 with vLLM, I saw basically the same behavior.
Re: best setup on 24GB VRAM - amberplane - 10-18-2026
Quote:[quote]What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there. A lot of these
Appreciate the detail. I ended up in about the same place using Ollama.