+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Edge AI & Gadgets (https://www.datasculpting.ai/inference/forumdisplay.php?fid=21)
+--- Forum: Mobile (https://www.datasculpting.ai/inference/forumdisplay.php?fid=73)
+--- Thread: running local models on a phone (/showthread.php?tid=846)
Pages:
1
2
running local models on a phone - batchpeak - 10-06-2026
Posting this in case it saves someone else a little time.
I'm helping a small team set up a local workflow. We don't need a giant stack, but we do care about tokens/sec.
I'm especially interested in mistakes worth avoiding.
Re: running local models on a phone - vramstream - 10-06-2026
I don't think that's the whole story. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.
Re: running local models on a phone - cozysmith - 10-06-2026
Quote:I don't think that's the whole story. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.
Appreciate the detail. I don't think your conclusion is far off.
Re: running local models on a phone - macrotinker - 10-06-2026
Not sure I agree there. I've seen people blame tool calling when the real issue was much more mundane. Worth testing the simpler explanation before adopting the more interesting one.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Re: running local models on a phone - northgrid33 - 10-07-2026
Good point. The pattern around router policy has been pretty similar for me.
Re: running local models on a phone - promptspark58 - 10-08-2026
Did a small comparison this afternoon. 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.
Re: running local models on a phone - turbosupply83 - 10-08-2026
Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.
Re: running local models on a phone - fastquill74 - 10-08-2026
Quote:Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Re: running local models on a phone - marbleyard32 - 10-08-2026
Appreciate the detail. The pattern around workstation thermals has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Re: running local models on a phone - promptspark58 - 10-09-2026
Not sure I agree there. I get why that seems right, but on 5090 the bottleneck felt elsewhere. Worth testing the simpler explanation before adopting the more interesting one.