How I Calculated the Optimal Context Size for My Local LLM
A practical walkthrough of calculating context window sizing for a local Qwen model on an RTX 5090
Recent Posts
Generating Cobra CLI Boilerplate with OpenCLI Specs
Generate boilerplate CLI code deterministically using OpenCLI specifications - contract-first and framework-agnostic
Experimenting with Local LLMs and VSCode
Experimenting with a local LLM and integrating with GitHub copilot in Visual Studio Code over LAN
OpenCLI Spec Is Now in Alpha
OpenCLI is now in alpha: a faster way to write, test, and share command-line workflows with an interactive editor.