+- 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 with PyTorch (/showthread.php?tid=1350)
Pages:
1
2
running local models on a phone with PyTorch - plainline - 10-16-2026
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 quant drift.
Would rather learn from your scars than collect my own all at once.
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Re: running local models on a phone with PyTorch - sparrowshed - 10-16-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there.
Re: running local models on a phone with PyTorch - relaysupply90 - 10-16-2026
Quote:What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there.
Good point. That matches what I saw on GB200. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: running local models on a phone with PyTorch - turbosupply83 - 10-18-2026
worth checking the driver first.
Re: running local models on a phone with PyTorch - cachebench - 10-18-2026
Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to matter more than it did.
Re: running local models on a phone with PyTorch - cudacrate - 10-18-2026
Quote:Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to
I hit almost the same issue last night.
Re: running local models on a phone with PyTorch - sparrowshed - 10-19-2026
A couple things I'd check first. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: running local models on a phone with PyTorch - fusedriver - 10-19-2026
Appreciate the detail. That matches what I saw on B200.
Re: running local models on a phone with PyTorch - sparrowworks88 - 10-19-2026
that fixed it for me too.
Re: running local models on a phone with PyTorch - plainline - 10-19-2026
A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?