mobile NPU reality check

[turbosupply83]

same here on my side.

[torchkite]

same here on my side.

same here on my side.

[cudacrate]

I'd approach it in a boring order. On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.

[routeline23]

I'd approach it in a boring order. On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not gla

subscribed, curious where this lands.

[batchpeak]

Need a little more detail here. Are you testing this on 4090 or something else?

[marbleyard32]

My first guess would be this: If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.