[magicalhippo]

Given that Ollama runs quite fine on Windows if you have NVIDIA, why such complicated setup?

It would make more sense for AMD I suppose where Ollama's Windows support is lacking compared to Linux.

That said, neat tricks useful for other stuff as well.

[laserbeam]

Yeah… was about to ask that. I just run Ollama on windows. What am I actually solving by running it virtualized in WSL?

[thot_experiment]

It's probably marginally faster for inference as long as you're willing to pay the extremely annoying cost of all the stupid filesystem issues. Given that ollama specifically has very good cross platform support it seems like a fool's errand.