+- 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: prompt length getting silly (/showthread.php?tid=216)
Pages:
1
2
prompt length getting silly - quiettoken - 09-11-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Just sharing a setup that ended up working reasonably well: Mistral, TensorRT-LLM, 7900 XTX, with a lot of attention on NVFP4.
If someone wants the exact settings I can clean them up and post them.
Re: prompt length getting silly - northgarden37 - 09-12-2026
What worked for me was pretty simple. If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: prompt length getting silly - quiettoken - 09-12-2026
Good point. I ended up in about the same place using TensorRT-LLM. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: prompt length getting silly - mlxgarden - 09-13-2026
Appreciate the detail. I ended up in about the same place using MLX.
Re: prompt length getting silly - mintstation99 - 09-13-2026
Interesting, I hadn't tried that. The pattern around workstation thermals has been pretty similar for me. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: prompt length getting silly - mlxgarden - 09-13-2026
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Phi and compare from there.
Re: prompt length getting silly - cozywire - 09-13-2026
What worked for me was pretty simple. If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: prompt length getting silly - rocmplane - 09-13-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at reranking. Once you know the plain path works, then add the faster path back in piece by piece.
Re: prompt length getting silly - batchember - 09-13-2026
What worked for me was pretty simple. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: prompt length getting silly - mlxgarden - 09-13-2026
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.