best small quant that still feels smart

[fusedtinker]

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

After a few runs on 5090, I ended up with decent performance, but the setup only really made sense once I adjusted around structured output.

Happy to post more details if anyone wants them.

I expected the biggest difference to come from the model, but the stack around it mattered at least as much.

[fusedtinker]

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

Appreciate the detail. That matches what I saw on 4090. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[torchshed]

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

A couple questions before I guess too hard. Are you testing this on A6000 or something else?

[oxiderunner]

I'd approach it in a boring order. If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.

[llmarch51]

Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher.

[nanobrook]

A couple things I'd check first. If you're on LM Studio, 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.

[marbletrack]

Need a little more detail here. Is this local-only or are you routing anything externally?

If you post your exact settings, people here can probably narrow it down pretty fast.

[mangofield33]

Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.

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

[turboscope]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.

[fastbench]

A couple things I'd check first. On GB200, 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.