John Paul Wile

I break things quickly and write about AI tech.

Full-Stack Developer & Writer · Colorado Springs, CO

Latest Posts

May 27, 2026

I’ve been running Qwen3.6-35B-A3B-MTP on my RTX 3070 (8GB VRAM) for a while now and previously documented getting ~55 tok/s....

May 20, 2026

PR #22673 just landed in upstream llama.cpp, and it is a big deal....

May 16, 2026

If you’ve been following the local LLM space this year, you’ve probably been tracking parameter counts, quantization methods, and hardware...

Full-Stack Developer & Tech Lead from Colorado Springs. I build things, break them, and write about what I learn along the way.

Get my latest thoughts on AI, development, and technology delivered to your inbox.