According to The Verge, 8GB of memory works mostly fine for basic tasks such as web browsing, text editing, and video streaming on YouTube and other streaming...
I have an 8gb M1 Mac mini that my dad gave me. Put Asahi on it with a view to using it for my Home Assistant server. That on its own was perfectly fine, but adding an LLM for voice commands absolutely fucked the RAM. No amount of swap or anything could help, it’d just hang.
So I set it back to macOS, because it can hook into Apple APIs for LLMs that utilise the GPU in a way that Asahi couldn’t. And yeah, Home Assistant + LLM runs really well even in a UTM VM. Same system, completely different outcomes.
And that’s no shade to Asahi. What they’ve achieve is little short of incredible, but there’s certain shit that Apple just won’t let them access.
I have an 8gb M1 Mac mini that my dad gave me. Put Asahi on it with a view to using it for my Home Assistant server. That on its own was perfectly fine, but adding an LLM for voice commands absolutely fucked the RAM. No amount of swap or anything could help, it’d just hang.
So I set it back to macOS, because it can hook into Apple APIs for LLMs that utilise the GPU in a way that Asahi couldn’t. And yeah, Home Assistant + LLM runs really well even in a UTM VM. Same system, completely different outcomes.
And that’s no shade to Asahi. What they’ve achieve is little short of incredible, but there’s certain shit that Apple just won’t let them access.