NVFP4 / INT4 tradeoffs

[deltagrid]

Has anyone else run into this?

I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling tool calling.

Would appreciate practical advice rather than theory.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.

[oxidestream]

Need a little more detail here. Are you testing this on dual 3090 or something else?

[vectorport]

Maybe, but I had the opposite result. I get why that seems right, but on 4090 the bottleneck felt elsewhere. Could be a workload difference, but I wouldn't generalize too fast from one setup.

[kernelmike]

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

[sanescope]

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

[rocmmixer]

Can you fill in a bit more context? Are you testing this on 7900 XTX or something else?

[amberplane]

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

[phaseport36]

I think the bottleneck is somewhere else. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Worth testing the simpler explanation before adopting the more interesting one.

[mellowwire98]

Good point. That matches what I saw on 7900 XTX.

[localpatch78]

Did a small comparison this afternoon. On 7900 XTX with SGLang, I saw basically the same behavior. The main thing that moved was latency, not quality.