DeepSeek V4.1 impressions

[llmarch83]

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

I tried this with Phi using llama.cpp on mini PC. The headline result was better than I expected, but INT4 still ended up being the limiting factor.

Curious if anyone else landed in the same place.

[routecraft]

I'd start with the simpler stack.

[routecraft]

I'd start with the simpler stack.

Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.