Setup guides
Choose a starting configuration and follow the steps to run your first model.
01
12–16 GiB GPUYour first local model
Start small, learn the runtime and use hardware you already have if possible.
Explore this path02
24–32 GiB GPUOne GPU, more room
A focused workstation for larger quantized models and local coding experiments.
Explore this path03
48 GiB aggregateThe two-GPU route
A conditional path to a larger model when one card is too small.
Explore this path04
Unified memoryA high-memory Mac workspace
Room for large model weights in a compact workstation, with a shared system memory budget.
Explore this path