CUDA update broke my throughput with Ollama

[edgecoast]

Interesting, I hadn't tried that. The pattern around consumer GPUs has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

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

[audiopath66]

My first guess would be this: If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.

[sparrowkite53]

I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher.

[stackarch]

My first guess would be this: If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.