TMD·Apr 16The Real Bottleneck of Local LLMs: It’s Not What You ThinkMASA Dev Log #1α — On Speed, Memory Bandwidth, and Hardware Daydreaming
InTowards AIbyTMD·Apr 16How I Built a Local LLM System on 16GB of RAM — And Why It Actually WorksA 9-layer AI system built with Ollama on a Mac mini M4. Architecture, failures, and what actually works.