The pitch for local LLMs in 2026
Why every engineer should run a local LLM in 2026: privacy, zero marginal cost, lower latency, no rate limits, and offline. Even a 16GB MacBook Air runs Llama 3.2 3B at 30 tok/s.
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 retain when you call an LLM API in 2026. What 'we don't train on your data' really means, free vs paid tier differences, and when local is the only safe option.
Why Apple Silicon punches above its weight on local LLMs
Unified memory means the GPU sees all of RAM. Why that beats discrete-GPU PCs above 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. The fastest GUI for running local LLMs — no terminal needed. Includes the local server for OpenAI-compatible API access.
Install llama.cpp
Build llama.cpp from source with Metal or CUDA acceleration. Run a GGUF model with llama-cli. The closest thing to bare-metal local inference.
Install Ollama
Install Ollama on macOS, Linux, and Windows. Pull your first model, run it locally, and verify with ollama list. The fastest path to a local LLM.