sqlite + embeddings surprisingly ok

[tinycontext]

I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.

[torchdesk]

Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?

[promptfield]

I don't think that's the whole story. 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.

[rocmriley]

Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.

[dockkite69]

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

[southspark]

that fixed it for me too.

[phasestream53]

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

One thing I keep noticing is that people underestimate NVFP4 until they actually try to run this stuff for more than one afternoon.

Maybe obvious to some of you, but it clicked for me this week.

[vrambandit]

same here on my side.

[routecraft]

Thanks, that helps. 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.

[rocmpath]

Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.