good hosted AI app that still respects privacy

[modrunner27]

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

It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with token cost.

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

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.

[latentcraft]

What worked for me was pretty simple. If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.

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

[dockriver]

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there. Not glamorous advice, but repeatable baselines save a lot of time. Turns out 'just one more test' was a lie.

[latentgarden]

That matches what I was seeing. I ended up in about the same place using vLLM. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[embershed99]

I hit almost the same issue last night.

[mintstation99]

I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Qwen and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.

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

[deepseeked]

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

[northhall88]

I tested this tonight. My result was mixed: first run looked bad, second run looked normal.

[cachebench]

That matches what I was seeing. I ended up in about the same place using TensorRT-LLM. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[paperrunner]

A couple things I'd check first. On 4090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.