After 8 months of running everything local, ive accepted the productivity tools also have to be local
Quick context: M3 max 64gb, currently running llama 3.3 70b q4 as my daily driver via ollama, qwen3 coder 30b for code (switched from qwen2.5 earlier this year), mlx for the smaller stuff. tried llama 4 scout earlier this year but 64gb is too tight at …