Claude Code on a Pixel 9 XL: Termux, a 125B Model, and a Mesh Network
Claude Code on a Pixel 9 XL through Termux, pointed at a 125B MoE on a GMKtec EVO-X2 over Headscale — the wrapper, the router, and the rough edges.
Qwen3.8-Flash-Next on the EVO-X2: 125B Parameters in 96GB of Unified Memory
What it took to run a 125B MoE model at 17-25 tok/s on a $3K mini PC — the BIOS carve-out, ROCm 7.2.4 on gfx1151, a llama.cpp grammar bug, and MTP.
Local LLM Inference on the GMKtec EVO-X2: ROCm, llama.cpp, and Real Numbers
How I got ROCm 7.2.4 working on gfx1151, built llama.cpp correctly for AMD Strix Halo, and what 67 tok/s on a mini PC actually means.
Building a Python MCP Server from Scratch
How I built and connected a working MCP server in Python — understanding the protocol, the tooling, and how it wires up to Copilot CLI over stdio.
Customizing the Swaybar: Battery and Volume from Scratch
How I built a minimal, fully understood swaybar status line with battery status, volume control, and mute detection — no plugins required.
Pitfalls Creating a Static Blog with SvelteKit and Copilot
Learn from my mistakes building a SvelteKit blog with AI assistance and deploying to Netlify. Avoid common pitfalls and configuration issues.
Building My First Blog: Learning to Code with AI
My journey creating a blog from scratch while embracing AI as a coding partner. Why I believe AI-assisted development is the future of programming.