Full AI Builder
fullThe complete local AI development stack: concurrent coding model + reasoning model + embeddings. Switch between QwQ for architecture decisions and Qwen Coder for implementation, with local RAG always available.
Concurrent VRAM
18.9 GB
Peak VRAM
18.9 GB
Min Bandwidth
500 GB/s
Models
4
VRAM Breakdown
How the 18.9 GB concurrent VRAM is used.
Always Running (Concurrent)
Switched (Loaded As Needed)
These share VRAM with the largest concurrent model. Only one runs at a time.
Q4_K_M
Q4_K_M
Q4_K_M
What matters most for this workflow
This workflow fits on surprisingly modest hardware, so the main decision is whether you want the cheapest workable setup or enough headroom to keep the experience snappy.
How to think about the hardware
This is one of the cleaner local-first cases: if you use the tools regularly, the economics catch up quickly and privacy/offline access become a bonus rather than the only justification.
Local vs API Costs
Typical Monthly API Cost
$150/mo
Break-Even Point
8 months
Annual Savings
~$1440/yr
Based on Cursor Pro ($20/mo) + heavy API usage with 32B coding + o1-mini reasoning (~$130/mo). AI Builder Workstation at $2,902. Break-even includes electricity (~$20/mo at 8hr/day). The privacy and latency advantages are significant: no rate limits, no outages, no data leaving your machine.
Recommended Builds
Pre-configured builds that can run the Full AI Builder workflow.
Prefer a Mac? Apple Silicon with unified memory can run this workflow too. See the Mac AI Builder workflow →