+- 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 llama.cpp (/showthread.php?tid=1319)
Pages:
1
2
desktop apps around local AI with llama.cpp - vramstream - 10-17-2026
Spent some time on this today and wanted to compare notes.
I'm comparing two approaches here: keep it simple on M3 Max, or squeeze more out of the stack and deal with the complexity.
What would you pick if you had to live with it for a few months?
Re: desktop apps around local AI with llama.cpp - torchshed66 - 10-17-2026
I think the bottleneck is somewhere else. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Re: desktop apps around local AI with llama.cpp - mlxgarden - 10-17-2026
Not sure I agree there. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.
Re: desktop apps around local AI with llama.cpp - vectorport - 10-17-2026
Interesting, I hadn't tried that. I ended up in about the same place using PyTorch. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: desktop apps around local AI with llama.cpp - batchshed - 10-17-2026
Need a little more detail here. Is this local-only or are you routing anything externally?
Re: desktop apps around local AI with llama.cpp - mlxgarden - 10-18-2026
Interesting, I hadn't tried that. That matches what I saw on mini PC.
Re: desktop apps around local AI with llama.cpp - mintstation99 - 10-18-2026
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at quant drift. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
I'm happy to test one more variant if you want a second data point.
Re: desktop apps around local AI with llama.cpp - modgarden - 10-18-2026
Quote:I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at quant drift. A lot of th
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Llama and compare from there. 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 llama.cpp - audionode8 - 10-18-2026
Interesting, I hadn't tried that. I don't think your conclusion is far off.
Re: desktop apps around local AI with llama.cpp - rocmhouse90 - 10-18-2026
Quote:[quote]I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at quant drift. A lo
Interesting, I hadn't tried that. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
If you post your exact settings, people here can probably narrow it down pretty fast.