Skip to content

Tag

#llama-cpp

Every story tagged llama-cpp, newest first.

Wooden and black electronic device with lens housing on wooden floor in home office
Tutorial · software

How to run a local LLM on your own machine with Ollama

Install Ollama on macOS, Windows or Linux, run Gemma 4 or Llama 3.2 with one command, check it uses your GPU, and call the local API on port 11434.

Ahmad J · Aug 13, 2026 · 4 min read

Two types of computer memory modules with gold connectors arranged on a gray surface, with a smaller chip positioned separately to the right
Tutorial · aiDeep read

How to choose the right quantization for a local LLM

Start with Q4_K_M. Use Q5_K_M if it still leaves room for your context, Q6_K over Q8_0, and IQ3_M or IQ2_M only when a model won't fit otherwise.

Ahmad J · May 24, 2026 · 4 min read