quant choices for 70B local

[southden]

Spent some time on this today and wanted to compare notes.

I'm comparing two approaches here: keep it simple on 7900 XTX, or squeeze more out of the stack and deal with the complexity.

What would you pick if you had to live with it for a few months?

This is mostly for local work rather than public serving.

[vramscope]

Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?

[benchplease]

Interesting, I hadn't tried that. I ended up in about the same place using SGLang.

[northquill]

Good point. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[southtinker]

My first guess would be this: On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.

[torchshed]

My first guess would be this: If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.

[circuitworks90]

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at workstation thermals. Not glamorous advice, but repeatable baselines save a lot of time.

[fusedtinker]

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at small local stacks. Once you know the plain path works, then add the faster path back in piece by piece.

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

[benchplease]

subscribed, curious where this lands.

[vrambandit]

I don't think that's the whole story. I get why that seems right, but on GB200 the bottleneck felt elsewhere. Worth testing the simpler explanation before adopting the more interesting one.