Install a local inference application, load a model, and verify the machine can answer prompts reliably
You should be able to demonstrate the result described in the lesson and explain why each step was necessary.
Step-by-step
Install LM Studio
Install the current build for your operating system and allow it to detect the available GPU backends.
Download a model
Choose a model and quantization that fits your memory budget. Verify the publisher and model family rather than downloading similarly named files blindly.
Load and test
Load the model, open a chat session, and begin with a short deterministic task so you can tell whether the model is behaving correctly.
Watch memory and speed
Observe VRAM/RAM consumption and tokens per second. If the system swaps heavily, use a smaller model or quantization.
Record settings
Save context size, GPU offload, temperature, and any other settings used for your benchmark.
You should be able to demonstrate the result described in the lesson and explain why each step was necessary.
Troubleshooting
If a command or screen differs from the lesson, stop and verify the version you are using before forcing a change.
What you learned
You now understand the purpose of this part of the system and have a concrete result you can verify before continuing to the next lesson.