Key Takeaways
- Home Assistant alone runs comfortably on a Raspberry Pi
- A mini PC is the better pick if you also want a local LLM, larger Whisper, or Frigate
- More RAM and a capable iGPU/NPU lower local-AI latency
- A NAS can host Home Assistant in a container alongside storage services
- A dedicated server suits larger, multi-service local setups
- Decide HA-only vs HA + AI before buying — it changes the right box
What the Hub Needs
Home Assistant itself is lightweight and runs on modest hardware; the heavy demands come from local AI and camera detection. Size the box for what you will add, not just the hub.
- The hub needs little compute for device control and automations.
- Local LLM inference, larger Whisper, and Frigate are the demanding workloads.
- Plan RAM and a GPU/NPU around those add-ons.
Raspberry Pi
A Raspberry Pi is the cheapest, lowest-power way to run Home Assistant for typical smart home use. It struggles with LLM inference and large Whisper models.
- Great for device control, automations, and a small local voice setup.
- LLM inference on a Pi is limited to very small, slow models.
- Choose a Pi if you want basics at low cost and power.
Mini PC (and Room for an LLM)
A mini PC is the best single-box choice for Home Assistant plus local AI, with enough RAM and a capable iGPU or NPU to run a small LLM. It balances power, size, and cost.
- Run Home Assistant, a small LLM via Ollama, Whisper, and Frigate together.
- Prioritise RAM and a capable integrated GPU or NPU for lower latency.
- For specific picks, see best mini PCs for Home Assistant + local AI and the cross-cluster best mini PCs for local LLMs.
NAS
A NAS can host Home Assistant in a container alongside storage and Frigate recordings, if it has enough CPU and RAM. It is convenient if you already own one.
- Good for combining storage with home automation services.
- Check the NAS has the CPU/RAM headroom for your add-ons.
- LLM inference on a NAS depends on its hardware — many lack a capable GPU.
Dedicated Server
A dedicated server suits larger setups running multiple services and a larger local model. It offers the most headroom at higher cost and power.
- Best for many cameras, a larger LLM, and multiple users.
- Higher power draw and cost than a mini PC.
- Overkill for a basic smart home — reserve for heavy local-AI use.
Picking for HA-only vs HA + AI
Choose a Pi for HA-only, and a mini PC for HA plus local AI — that single decision drives the right hardware. Match the box to the workload.
| Hardware | Relative price | HA-only | Can run a local LLM | Notes |
|---|---|---|---|---|
| Raspberry Pi | Low | Yes | Very small only, slow | Lowest power |
| Mini PC | Medium | Yes | Yes (small models) | Best single-box for HA + AI |
| NAS | Medium–High | Yes (container) | Depends on hardware | Combines storage + HA |
| Dedicated server | High | Yes | Yes (larger models) | Most headroom, most power |
FAQ
Can a Raspberry Pi run a local LLM too?
A Pi can run only very small models, and slowly, so it is not ideal for a responsive local-LLM assistant. It handles Home Assistant and basic voice well, but for local AI a mini PC with a capable iGPU or NPU is the better choice.
How much RAM do I need?
Home Assistant alone runs in a couple of gigabytes. To run a small local LLM and other AI services on the same box, more RAM helps; a mini PC with ample RAM and a capable iGPU/NPU keeps a small model responsive. Match RAM to the model size you plan to run.
What mini PC should I get?
Choose a mini PC with enough RAM and a capable integrated GPU or NPU for the model size you want. See the best mini PCs for Home Assistant + local AI guide for picks matched to HA plus a small LLM.
One box or two?
One box (a mini PC) is simplest and runs Home Assistant plus a small local LLM together. Split into two if you want to keep the hub ultra-reliable on a Pi and offload heavy AI to a separate, more powerful machine.