An apparently silly GET-only service reveals how model weights move from one machine to another. This guide explains chunks, Base64, GGUF, llama.cpp, and the security problems created when URLs perform writes and inference.
macOS VMs on Apple Silicon can run LLM inference far faster when the guest reports conservative Metal capabilities. A process-scoped capability shim steers llama.cpp onto newer Metal kernels, yielding reported 11–16× speedups while keeping the same Virtualization.framework GPU path.
Qwen 3.6 27B stands out as a practical local model: high enough quality for day-to-day development and strong performance with llama.cpp. This guide explains why 27B is the sweet spot and shows how to run it (with MTP) and integrate it into coding tools.