{"Projects":[],"Insights":[{"title":"Cut Your Coding-Agent Bill, Part 3: Run the Loop on Your Own Hardware","description":"Part 3 of 3: take the agent loop fully local. Ollama, llama.cpp and vLLM, quantization and VRAM math explained, the OpenAI-compatible local endpoint, and exactly when owning the hardware beats renting tokens.","url":"/blog/technology/cut-your-coding-agent-bill-part-3","tags":["AI","Coding Agents","Local LLMs","Cost"],"category":"Insights"}],"Personal":[],"Big Ideas":[],"Tools":[{"title":"Can I run this LLM? (VRAM)","description":"GPU memory a model needs, whether it fits your card, and how many GPUs.","url":"/tools/vram-calculator","tags":["vram","gpu","local","llm"],"category":"Tools"}]}