Rig Finder index / 8B / Local RAG / knowledge base / Ohio
Best rig to run an 8B model for local rag / knowledge base in Ohio
For an 8B model at this workload, the Mini-PC pays off fastest — break-even ~4 months, keeping $6,920 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 an 8B 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 | 8B tok/s | Local/mo | Break-even | Verdict |
|---|---|---|---|---|---|
| Mini-PCbest payoff | $750 | 22estimated | $23.77 | ~4 mo | OWN |
| RTX 3090 (used) | $1,200 | 85estimated | $46.86 | ~6 mo | OWN |
| RTX 4090 | $2,300 | 120estimated | $78.89 | ~11 mo | OWN |
| 2× RTX 3090 | $2,250 | 90estimated | $85.39 | ~12 mo | OWN |
| Mac M-series | $3,000 | 65estimated | $86.04 | ~14 mo | OWN |
| RTX 5090 | $3,500 | 180estimated | $116 | ~18 mo | OWN |
Assumes local rag / knowledge base use: ~40M tokens/month, 5h/day active, 11h/day idle, at Ohio electricity ($0.161/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 →