memory layers vs plain long context

[circuitkite]

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

I've gone back and forth between llama.cpp and llama.cpp for DeepSeek. The interesting difference for me has been quant drift.

What would you pick if you had to live with it for a few months?

[edgequill]

that fixed it for me too.

[quantghost]

What worked for me was pretty simple. If you're on Ollama, 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. At this point the real bottleneck is my patience.

[tinycontext]

worth checking the driver first.

[bytesupply76]

Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.

[flintriver50]

Interesting, I hadn't tried that. I ended up in about the same place using LM Studio.