> For the complete documentation index, see [llms.txt](https://intelfactor.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://intelfactor.gitbook.io/docs/home/architecture/hardware-tiers.md).

# Hardware tiers

A practical framework for Jetson sizing.

Hardware selection should match line speed, camera count, and compute headroom.

### Tier 1: Single-station pilot

* Prove the inspection loop on one station.
* Basic detection + rules + local evidence storage.

### Tier 2: Production scale (default)

* Detection + local RCA + local UI.
* Headroom for concurrent workloads.

### Tier 3: Multi-line site hub (future)

* Multi-line aggregation.
* Larger local models.
* Site-wide dashboard and model registry.

### Tier 4: Enterprise site server (future)

* Larger on-prem models.
* Fleet reporting and longer-term analytics.

**Principle:** start with what is deployed. Upgrade only when compute is the bottleneck.