Ollama for power users on 5090

[fusedhall]

Did a bit of testing and thought I'd post the result here.

Short version: TensorRT-LLM behaved well for me, but only after I stopped ignoring structured output.

Happy to post more details if anyone wants them.

[mangofield33]

Can you fill in a bit more context? Are you testing this on dual 3090 or something else?

[localcraft17]

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tail latency.

[cudapeak]

I don't think that's the whole story. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.

[cacheline]

worth checking the driver first.

[edgekite]

What worked for me was pretty simple. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives.

[vectorhouse71]

That matches what I was seeing. I ended up in about the same place using MLX. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[latentscope35]

I hit almost the same issue last night.