benchmark result I don't trust: early impressions

[deltastation]

My first guess would be this: On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives.

[deltastation]

I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at long context.

[northgrid33]

I don't think that's the whole story. I get why that seems right, but on mini PC the bottleneck felt elsewhere.