industry move that matters for local users

[quietstack]

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? At this point the real bottleneck is my patience.

[orbitgarden]

I don't think that's the whole story. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.

[phaseshed]

worth checking the driver first.

[amberrunner]

worth checking the driver first.

same here on my side.

I'm happy to test one more variant if you want a second data point.

[deepseeked]

Interesting, I hadn't tried that. I ended up in about the same place using vLLM.

[bytelab]

I'd start with the simpler stack.

[modbench]

Thanks, that helps. I ended up in about the same place using LM Studio. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[deepseeked]

Appreciate the detail. That matches what I saw on mini PC.

[bytestack]

Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal.

[fastlab]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.