+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Apps / Utilities / Tools (https://www.datasculpting.ai/inference/forumdisplay.php?fid=18)
+--- Forum: Local (https://www.datasculpting.ai/inference/forumdisplay.php?fid=20)
+--- Thread: desktop apps around local AI with LM Studio (/showthread.php?tid=52)
Pages:
1
2
desktop apps around local AI with LM Studio - rocmcrate26 - 08-28-2026
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: Phi, vLLM, dual 3090, with a lot of attention on tail latency.
Maybe useful as a starting point for newer folks.
My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
Re: desktop apps around local AI with LM Studio - rocmriley - 08-28-2026
Quote:Thought I'd post a small recipe because a lot of threads ask similar things.
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
Re: desktop apps around local AI with LM Studio - audionode8 - 08-29-2026
Quote:Quote:Thought I'd post a small recipe because a lot of threads ask similar things.
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at long context.
Re: desktop apps around local AI with LM Studio - mintstation99 - 08-29-2026
A couple questions before I guess too hard. What model, what runtime, and roughly what context size?
Re: desktop apps around local AI with LM Studio - batchshed - 08-31-2026
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: desktop apps around local AI with LM Studio - amberpatch25 - 08-31-2026
Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.
Re: desktop apps around local AI with LM Studio - mangoquill - 09-01-2026
Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?
Re: desktop apps around local AI with LM Studio - mlxgarden - 09-02-2026
A couple things I'd check first. On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: desktop apps around local AI with LM Studio - rocmhouse90 - 09-05-2026
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at KV cache pressure. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: desktop apps around local AI with LM Studio - cachebench - 09-05-2026
Quote:My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at KV cache pressure. A lot of t
Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.