Rig Finder index / 32B / Casual chat / District of Columbia
Best rig to run a 32B model for casual chat in District of Columbia
At this usage, renting Claude Sonnet 4.6 beats owning for every rig that runs a 32B model. The least-bad build is the RTX 3090 (used), but that's a sovereignty call, not a savings one.
Same workload, same cloud, same electricity — we swap only the hardware and rank by real break-even. Rigs that can't run a 32B model are shown, never recommended. Compared against Claude Sonnet 4.6 ($3/M in, $15/M out); change the cloud in the lab.
Every build, ranked
| Rig | Build | 32B tok/s | Local/mo | Break-even | Verdict |
|---|---|---|---|---|---|
| RTX 3090 (used)best payoff | $1,200 | 24estimated | $36.61 | ~68 mo | RENT |
| RTX 4090 | $2,300 | 38estimated | $67.52 | ~132 mo | RENT |
| 2× RTX 3090 | $2,250 | 30estimated | $68.07 | ~146 mo | RENT |
| Mac M-series | $3,000 | 20estimated | $83.99 | ~148 mo | RENT |
| RTX 5090 | $3,500 | 60estimated | $102 | ~213 mo | RENT |
| Mini-PCtoo small for 32B | $750 | — | $21.55 | ~37 mo | RENT |
Assumes casual chat use: ~3M tokens/month, 1h/day active, 3h/day idle, at District of Columbia electricity ($0.182/kWh). Speeds are our estimates; community-measured tok/s live on the interactive Rig Finder and the benchmarks board. Every formula is on the methodology page.
Run this with your exact numbers →