Minimum sensible
The smallest build that genuinely works — tight, focused, no fluff.
- CPU
- 4 cores
- RAM
- 8 GB
- Storage
- 1 TB (ssd)
- GPU
- dedicated · 4 GB VRAM
- Network
- 1 GbE
Service → hardware · AI
Frigate: hardware requirements
Local AI object detection on camera feeds — people, vehicles, no cloud.
Recommended
The sweet spot: handles the service plus the usual side-services.
- CPU
- 8 cores
- RAM
- 16 GB
- Storage
- 2 TB (ssd)
- GPU
- dedicated · 6 GB VRAM
- Network
- 2.5 GbE
Comfortable
Real headroom — this service will never be the bottleneck.
- CPU
- 12 cores
- RAM
- 32 GB
- Storage
- 4 TB (ssd)
- GPU
- ai · 12 GB VRAM
- Network
- 2.5 GbE
Overkill
More than you will ever use for this service alone — spend the money elsewhere.
- CPU
- 20 cores
- RAM
- 52 GB
- Storage
- 8 TB (ssd)
- GPU
- ai · 12 GB VRAM
- Network
- 2.5 GbE
Overkill Beyond Comfortable — 12 cores, 32 GB RAM, 4 TB: headroom you will never use for this service alone.
Size it exactly
Coral TPU needs no GPU at all; GPU detection needs VRAM.
No discrete GPU needed for this choice.
Runs well with
Related services
About this tool
Frequently asked questions
How much RAM does Frigate need?
8 GB is the sensible minimum, 16 GB covers most real setups, and 32 GB gives comfortable headroom.
How many CPU cores does Frigate need?
4 cores are the minimum, 8 cores the sweet spot, and 12 cores comfortable when shared with other services.
Can I run several services on one machine?
Yes — most services share resources. Use the planner and select several services; the engine sums and overlaps the requirements instead of stacking them.
What if I already have hardware?
Register it in My hardware and the analysis shows exactly which services your current system can comfortably run — including an honest “do nothing”.