LM Studio surprisingly handy on M3 Max

[vectorcrate98]

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: Kimi, vLLM, dual 3090, with a lot of attention on NVFP4.

Feel free to tear it apart if you see something dumb.

[oxidestream]

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.

[edgeriver]

What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Llama and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.

[kernelgrid]

I'd approach it in a boring order. If you're on SGLang, 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.

[mellowwire98]

Good point. I ended up in about the same place using SGLang.

[promptspark58]

same here on my side.

[dockridge]

My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at small local stacks.

[mellowwire98]

My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at small local stacks.

subscribed, curious where this lands.