benchmark result I don't trust for FLUX

[quiethouse]

This keeps coming up in conversation so I figured I'd start a thread.

The more I work with local setups, the more it seems like NVFP4 decides everything downstream.

Wondering if this is just where the whole space is heading now.

[batchsize]

Maybe, but I had the opposite result. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.

I'm happy to test one more variant if you want a second data point.

[benchplease]

Maybe, but I had the opposite result. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.

[cacheline]

What exact setup are you running? What model, what runtime, and roughly what context size?

[kernelghost]

What exact setup are you running? What model, what runtime, and roughly what context size?

I hit almost the same issue last night. Turns out 'just one more test' was a lie.

[batchpeak]

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.

[cacheline]

Good point. I ended up in about the same place using llama.cpp. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[oxiderunner]

Not sure I agree there. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Worth testing the simpler explanation before adopting the more interesting one.

[cacheline]

Appreciate the detail. I ended up in about the same place using LM Studio. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[quiethouse]

My first guess would be this: On 7900 XTX, 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.