memory layers vs plain long context

[sparrowghost]

Did a bit of testing and thought I'd post the result here.

After a few runs on 7900 XTX, I ended up with decent performance, but the setup only really made sense once I adjusted around NVFP4.

Curious if anyone else landed in the same place.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.

[tinycontext]

A couple questions before I guess too hard. What model, what runtime, and roughly what context size?

There are a few different conversations hiding inside this thread, so being explicit about the goal helps.