which local open model do you keep coming back to: anyone testing this?

[cacheworks]

Thought I'd post a small recipe because a lot of threads ask similar things.

Maybe useful as a starting point: TensorRT-LLM on Threadripper box, keeping long context in mind from the start.

Maybe useful as a starting point for newer folks.

I care more about stability than squeezing the last possible tokens/sec out of it.