good hosted AI app that still respects privacy

[modrunner27]

Spent some time on this today and wanted to compare notes.

I've gone back and forth between llama.cpp and MLX for FLUX. The interesting difference for me has been INT4.

Trying to avoid rebuilding the whole thing twice.

[mangovault67]

Tried to reproduce it just now. On 7900 XTX with Ollama, I saw basically the same behavior. The main thing that moved was latency, not quality.

[audiodesk]

Thanks, that helps. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[cachebench]

My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tokens/sec. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[promptfield]

I tested this tonight. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did. I keep promising myself this is the last rebuild.

[quantyard]

Appreciate the detail. That matches what I saw on A6000. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[thetarunner]

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at INT4. Not glamorous advice, but repeatable baselines save a lot of time.

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

[cudapeak]

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at INT4. Not glamorous a

What worked for me was pretty simple. On 7900 XTX, the easiest win is often to back off the aggressive settings and see whether the problem survives.

[modrunner27]

Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed.

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

[mintstation99]

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. Worth testing the simpler explanation before adopting the more interesting one.

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