NVIDIA driver regression with MLX

[sparrowkite53]

Posting this in case it saves someone else a little time.

I'm helping a small team set up a local workflow. We don't need a giant stack, but we do care about embeddings.

Would rather learn from your scars than collect my own all at once.

[edgecoast]

Posting this in case it saves someone else a little time.

Thanks, that helps. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[amberpatch25]

Interesting, I hadn't tried that. I ended up in about the same place using llama.cpp. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.