tools worth paying for on 5090

[emberrunner]

Curious what people here are seeing.

I'm mostly working with Mistral in MLX on A6000. The part I'm trying to understand is router policy.

Would appreciate practical advice rather than theory.

[southpatch]

Curious what people here are seeing.

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.

[torchsmith25]

Curious what people here are seeing.

Need a little more detail here. Are you testing this on A6000 or something else?

[promptfield]

same here on my side.

[vramarch]

My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at continuous batching. Once you know the plain path works, then add the faster path back in piece by piece.

[thetashed24]

subscribed, curious where this lands.

[macrostack69]

Appreciate the detail. The pattern around NVFP4 has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[bytelab]

What worked for me was pretty simple. If you're on llama.cpp, 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.

[southpatch]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[tensorriver]

that fixed it for me too.