The pitch for local LLMs in 2026
The case for running an LLM on the machine you already own. Privacy, no per-call cost, faster first token, no rate limits, and it works on a flight.
Blog
#local-models
Posts on AI engineering, LLM systems, and software development.
What leaves your machine when you use AI
What providers actually see, log, and keep when you call an LLM API in 2026. What "we don't train on your data" really means, how free and paid tiers differ, and when local is the only safe choice.
Why Apple Silicon punches above its weight on local LLMs
Unified memory lets the GPU see all of RAM. Here's why that beats a discrete-GPU PC past 32B parameters, what fits in 16/32/64/128/192GB, and where Apple Silicon still loses.
Install LM Studio
Install LM Studio on macOS, Linux, and Windows, then flip on the local OpenAI-compatible server so any client library can talk to a model on your own machine.
Install llama.cpp
Build llama.cpp from source with Metal or CUDA, then run a GGUF model with llama-cli. The closest thing to bare-metal local inference.
Install Ollama
Get Ollama running on macOS, Linux, or Windows, pull your first model, and confirm it works with ollama list. The shortest path to a local LLM.