good hosted AI app that still respects privacy for Mistral

[rocmpath]

I think the bottleneck is somewhere else. I've seen people blame workstation thermals when the real issue was much more mundane. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.

[latentgarden]

What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?

[sparrowshed]

same here on my side.

[thetarunner]

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at token cost. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

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

[mintstation99]

following this because I'm in the same boat.

[mangopeak72]

following this because I'm in the same boat.

I'd approach it in a boring order. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives.