VRAM Guides
Best Local AI Models by VRAM
The biggest question in local AI is simple: what actually fits my GPU? These guides answer it per VRAM tier with hand-verified footprints, real tokens/sec (or seconds per image), a clear winner, and what won't fit.
General LLM
Coding LLM
Flux image
Qwen
Stable Diffusion
Ollama
Once your hardware is sorted
Know what to actually run on it
All 561 chapters — running local models, RAG, agents, fine-tuning — plus the Python Lab and every course added later.
$149 once unlocks everything, forever — about $0.27/chapter for life. Prefer to spread it out? Pro is $79/year (saves 27%) or $8.99/month.
Secure checkout by Lemon Squeezy — your card never touches this siteInstant access the moment you payFirst chapter of every course is free — try before you buy
Prefer to browse by the exact card or Mac you own? See the picks per GPU (RTX 3060/4060/4070/4090) and picks per Mac (16GB and 32GB Apple Silicon).