Neither Anthro nor OAI are trustworthy. Local AI all the way. And when I say local, I mean Apple Silicon; I don't like to contribute to Nvidia's monopoly either (fuck "buy a GPU"; the guy is an Nvidia-sponsored "influencer").
Neither Anthro nor OAI are trustworthy. Local AI all the way. And when I say local, I mean Apple Silicon; I don't like to contribute to Nvidia's monopoly either (fuck "buy a GPU"; the guy is an Nvidia-sponsored "influencer").
What are you having good luck with on Apple Silicon? Or is this more of a statement for when local AI becomes “good enough?”
(FWIW I am with you; I haven’t found a local model that works well enough to be a daily driver)
qwen models are basically <opus and >sonnet. 397b runs at Q8 on m3 ultra. for mbp m5 max I'd use the +120b qwen model.