high-context local setup for Llama

[modrunner27]

I tested this tonight. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.

I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at quant drift. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.