• 

  What Does a Local LLM Token Cost? Measuring Qwen-Class Inference with Prometheus and Grafana

  Oct 15, 2026

• 

  Choosing a Local LLM Runtime: From LM Studio to vLLM, llama.cpp, and Unsloth Desktop

  Oct 8, 2026

• 

  Building a Local LLM Server: The Tradeoffs Behind My Hardware Choices

  Oct 1, 2026

• 

  Markdown Style Guide

  Jun 19, 2024

• 

  Using MDX

  Jun 1, 2024