Rig Finder index / 32B / Always-on agent server / South Dakota

Best rig to run a 32B model for always-on agent server in South Dakota

For a 32B model at this workload, the RTX 3090 (used) pays off fastest — break-even ~2 months, keeping $21,841 over 3 years versus Claude Sonnet 4.6.

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

RigBuild32B tok/sLocal/moBreak-evenVerdict
RTX 3090 (used)best payoff $1,200 24estimated $53.30 ~2 mo OWN
2× RTX 3090 $2,250 30estimated $96.14 ~4 mo OWN
RTX 4090 $2,300 38estimated $86.05 ~4 mo OWN
Mac M-series $3,000 20estimated $87.33 ~5 mo OWN
RTX 5090 $3,500 60estimated $125 ~6 mo OWN
Mini-PCtoo small for 32B $750 $25.13 ~1 mo OWN

Assumes always-on agent server use: ~120M tokens/month, 10h/day active, 14h/day idle, at South Dakota electricity ($0.128/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 →

Related