best local stack on mac right now on 5090

[plainember52]

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

Just sharing a setup that ended up working reasonably well: DeepSeek, LM Studio, B200, with a lot of attention on continuous batching.

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

I care more about stability than squeezing the last possible tokens/sec out of it.

[dockridge]

I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.

[sanescope]

Interesting, I hadn't tried that. That matches what I saw on 5090. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[dockridge]

A couple things I'd check first. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious.

[pixelcrate82]

Can you fill in a bit more context? Are you testing this on B200 or something else?

[amberplane]

Good point. That matches what I saw on A6000.

[mlxgarden]

That matches what I was seeing. I ended up in about the same place using TensorRT-LLM.

[signalpeak]

Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.

[plainember52]

Appreciate the detail. That matches what I saw on 5090. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[cobalttinker]

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. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.