+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Prompting & Context Engineering (https://www.datasculpting.ai/inference/forumdisplay.php?fid=15)
+--- Forum: Prompts / System Prompts (https://www.datasculpting.ai/inference/forumdisplay.php?fid=62)
+--- Thread: few-shot when you actually need it (/showthread.php?tid=339)
Pages:
1
2
few-shot when you actually need it - quiettoken - 09-18-2026
Did a bit of testing and thought I'd post the result here.
After a few runs on 5090, I ended up with decent performance, but the setup only really made sense once I adjusted around long context.
Curious if anyone else landed in the same place.
Re: few-shot when you actually need it - mangofield33 - 09-18-2026
Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Re: few-shot when you actually need it - promptspark58 - 09-18-2026
That matches what I was seeing. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: few-shot when you actually need it - mlxgarden - 09-18-2026
A couple questions before I guess too hard. Is this local-only or are you routing anything externally?
Re: few-shot when you actually need it - quiettoken - 09-19-2026
Good point. That matches what I saw on 7900 XTX. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: few-shot when you actually need it - batchember - 09-20-2026
same here on my side.
Re: few-shot when you actually need it - thetafield - 09-21-2026
Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?
Re: few-shot when you actually need it - cozywire - 09-23-2026
Quote:Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?
My first guess would be this: If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: few-shot when you actually need it - batchember - 09-23-2026
A couple things I'd check first. On 4090, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: few-shot when you actually need it - quiettoken - 09-23-2026
same here on my side.