Run your first model with Ollama
Install Ollama, download a small model, and get a reply from your terminal.
Learning path
Set up & run
Pick a graphical app or a terminal workflow. Get your first reply, check hardware acceleration, and connect a client to your runtime.
Choose a runtime
5 lessonsGet started with LM Studio
Download, load, and chat with a local model through a desktop interface.
Run a GGUF model with llama.cpp
Choose a llama.cpp build, load an explicit model file, and control context from the command line.
Run a model with MLX on Apple silicon
Install MLX LM in a Python environment, generate a reply, and reuse the model from the local cache.
Run on the CPU and check GPU offload
Use one GGUF file to compare CPU inference with GPU offload, then inspect the runtime’s reported placement.
Connect to a model
4 lessonsCall a local model from Python
Send a request to Ollama over localhost and read the reply in a small Python script.
Use one local client with several runtimes
Run Chat Completions against Ollama and llama.cpp, then use the same client with LM Studio’s local server.
Use a model on your own second computer
Connect to an Ollama instance over SSH while keeping the model server bound to the host’s loopback address.
Require a key for a local model server
Start a loopback llama.cpp server with authentication and verify that model requests require the key.