24.6× cheaper than cloud
$0.41 / 1M tokens local
Top models you can run
- SQwen 3 8B· 112 tok/s · 21K ctx · 8B params
- SQwen 3.5 9B· 113 tok/s · 17K ctx · 9B params
- SQwen 3.5 4B· 56 tok/s · 39K ctx · 4B params
Interactive tool
What should I buy for local AI?
Tell us your budget and what you'll use it for. We'll rank GPUs and Macs by how well they run models for that workload, show you which specific models will run great, and compare cost-per-token against cloud APIs.
Top 5 picks for $500 / general chat
16.5× cheaper than cloud
$0.61 / 1M tokens local
Top models you can run
- SQwen 3.5 9B· 47 tok/s · 30K ctx · 9B params
- SQwen 3 8B· 52 tok/s · 34K ctx · 8B params
- SQwen 3.5 4B· 56 tok/s · 52K ctx · 4B params
17.9× cheaper than cloud
$0.56 / 1M tokens local
Top models you can run
- SQwen 3.5 9B· 43 tok/s · 32K ctx · 9B params
- SQwen 3 8B· 48 tok/s · 37K ctx · 8B params
- SQwen 3.5 4B· 56 tok/s · 54K ctx · 4B params
23.3× cheaper than cloud
$0.43 / 1M tokens local
Top models you can run
- SQwen 3.5 4B· 56 tok/s · 26K ctx · 4B params
- SPhi-4 Mini Reasoning 4B· 53 tok/s · 40K ctx · 3.799999952316284B params
- SQwen 3 4B· 56 tok/s · 26K ctx · 4B params
18.2× cheaper than cloud
$0.55 / 1M tokens local
Top models you can run
- SQwen 3.5 4B· 56 tok/s · 26K ctx · 4B params
- SPhi-4 Mini Reasoning 4B· 53 tok/s · 40K ctx · 3.799999952316284B params
- SQwen 3 4B· 56 tok/s · 26K ctx · 4B params
How we rank
We filter hardware by MSRP under your budget, then score each candidate by the best-fit model for your workload — combining fit status (native / tight / offload), decode throughput, VRAM utilization, and model quality tier. ROI uses $10/1M tokens as the cloud reference (GPT-4o / Claude Sonnet tier) with 36-month amortization and $0.15/kWh electricity. Used-market prices are flagged when applicable (e.g., RTX 3090 at ~$800).
See also