To run this model locally at gpt4 writing speed you need at least 2 x 3090 or 2 x 7900xtx. VRAM is the limiting factor in 99% of cases for interference. You could try a smaller model like mistral-instruct or SOLAR with your hardware though.

I put zorin on my parent's computer 2 years ago, while its a great distro, their windows app support is just marketing, its an out of date wine version with an unmaintained launcher. Worse than tinkering with wine yourself.

It is already here, half of the article thumbnails are already AI generated.

It works with plugin juste like obsidian, so if their implémentation is not gold enough, you can always find a gramarly plugin.

It does not work exactly like obsidian as it is an outliner. I use both on the same vault and logseq is slower on larger vault.

Do you use comfyui ?

You are easier to track with Adnauseum

Being able to run benchmarks doesn't make it is a great experience to use unfortunately. 3/4 of applications don't run or have bugs that the devs don't want to fix.

Windows is not fine with ARM, which can be a turnoff for some.

Llama models tuned for conversation are pretty good at it. ChatGPT also was before getting nerfed a million time.

Even dumber than that, when their activation method fail, the support uses massgrev to install windows on costumer pc