+- 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: system prompt habits that helped on M3 Max (/showthread.php?tid=424)
Pages:
1
2
system prompt habits that helped on M3 Max - cozywire - 09-22-2026
This keeps coming up in conversation so I figured I'd start a thread.
The more I work with local setups, the more it seems like continuous batching decides everything downstream.
Curious whether that lines up with what other people are seeing.
Re: system prompt habits that helped on M3 Max - paperport64 - 09-23-2026
worth checking the driver first.
Re: system prompt habits that helped on M3 Max - thetafield - 09-23-2026
My first guess would be this: On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
Re: system prompt habits that helped on M3 Max - mlxgarden - 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: system prompt habits that helped on M3 Max - batchscope72 - 09-24-2026
A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?
Re: system prompt habits that helped on M3 Max - fusedhall56 - 09-24-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at embeddings. Not glamorous advice, but repeatable baselines save a lot of time.
Re: system prompt habits that helped on M3 Max - thetafield - 09-27-2026
Appreciate the detail. That matches what I saw on 4090. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: system prompt habits that helped on M3 Max - northgarden37 - 09-28-2026
Thanks, that helps. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: system prompt habits that helped on M3 Max - rasterhall - 09-28-2026
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
Re: system prompt habits that helped on M3 Max - fusedhall56 - 09-28-2026
My first guess would be this: If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.