When Local LLMs Actually Cut Cloud Costs for Coding
Birgitta Böckeler details the hardware and performance trade‑offs of running 15‑25 GB local LLMs on Apple M3 Max and M5 Pro machines. She finds RAM is the main bottleneck, speed has improved dramatically, but agentic coding still stumbles on tool‑calling. The memo helps developers decide when a local model can replace costly cloud APIs.