small win thread on 5090

[quiettoken]

Thought I'd post a small recipe because a lot of threads ask similar things.

Maybe useful as a starting point: MLX on 5090, keeping long context in mind from the start.

If someone wants the exact settings I can clean them up and post them.

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.

[quiettoken]

I think the bottleneck is somewhere else. I get why that seems right, but on mini PC the bottleneck felt elsewhere. Could be a workload difference, but I wouldn't generalize too fast from one setup.

[cudacrate]

Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.

[latentscope35]

I think the bottleneck is somewhere else. I get why that seems right, but on A6000 the bottleneck felt elsewhere. Could be a workload difference, but I wouldn't generalize too fast from one setup.

[cacheplane98]

I hit almost the same issue last night.

[marbletrack]

Thanks, that helps. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

There are a few different conversations hiding inside this thread, so being explicit about the goal helps.

[ggufwire22]

Interesting, I hadn't tried that. That matches what I saw on mini PC. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[cacheplane98]

I'd approach it in a boring order. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious.

[quiettoken]

Can you fill in a bit more context? Is this local-only or are you routing anything externally?

[plaingarden18]

Thanks, that helps. I don't think your conclusion is far off.