Model Architectures · Practitioner
Local & Open-Weight Models: Ollama, llama.cpp and When to Self-Host
Run open-weight models on your own hardware, understand quantisation formats and VRAM math, and decide when self-hosting wins.
- 45 min lesson
- intermediate level
- Engineering Track
- Narrated presentation
What you’ll learn
- GGUF, llama.cpp and Ollama
- Quantisation levels and quality trade-offs
- VRAM estimation and KV cache
- Throughput serving with vLLM/TGI
- Data residency and privacy drivers
- Break-even analysis vs. hosted APIs
Inside this lesson
A narrated, slide-by-slide presentation with 1 prediction exercise, 1 knowledge check, 5 videos. You answer as you go, and the platform checks your work.