Back to Curriculum Skill Map
Module 10Advanced
Local AI Deployment
Deploy offline runtimes with Ollama, LM Studio, llama.cpp, quantization trade-offs, local RAG, and GPU containerization.
Module Completion0 of 5 Topics (0%)
Topic Lessons (5)
21.
Runtimes & Models
20m •Ollama, LM Studio, llama.cpp, GGUF models, and quantization.
20m
22.
Hardware Planning
20m •Sizing CPU/GPU, VRAM, and RAM for 7B, 14B, and 70B models.
20m
23.
Local RAG & Embeddings
20m •Fully offline retrieval pipelines and local vector databases.
20m
24.
Containerization
25m •Dockerizing AI stacks, Docker Compose, and GPU passthrough.
25m
25.
Production Readiness
20m •Performance tuning, monitoring, and security for on-prem AI.
20m