Artificial Intelligence

Understand AI.
Run it locally.

The first E—DOCEO AI track focuses on local inference: the concepts, hardware constraints, model formats, runtime setup and measured behavior on real hardware.

Knowledge track

Local AI

Start with fundamentals, then move through hardware, VRAM, quantization, GGUF and Ollama.

Explore Local AI →
Structured path

Learn in order

An eight-step path from the basic concept to a running model and real Lab measurements.

Open learning path →
Verified tutorial

Install Ollama on Windows

Install, verify the CLI, run a model and call the local HTTP API.

Follow tutorial →
DOCEO LAB

See measured results

Reproducible Gemma 3 1B and Qwen3 4B tests on a GTX 1060 3GB.

Open Lab →