best setup on 24GB VRAM: early impressions

[deepseeked]

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.

[fastquill74]

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.

[deepseeked]

I hit almost the same issue last night.

[northcraft90]

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.

[promptfield]

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.

[latentcraft]

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.

[macropilot]

I'd start with the simpler stack.

[deepseeked]

I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there.

[embershed99]

What exact setup are you running? Is this local-only or are you routing anything externally?

[macrolab]

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.