AI models
Local models
Run camera AI on your own computer: frames stay on your premises and there is no token bill.
What a local model does
With a local model, your Station analyses camera frames on the same computer it runs on. The frames are masked and prepared exactly as for cloud providers, then answered by the model in place. They are never sent to a cloud AI provider.
Your workspace still receives the answers, so you get the same Messages, incidents, Push notifications, Webhooks and history. Snapshots stay on the Station, as always.
Supported models
Qwen 3.5 9B (recommended): about 6.6 GB to download. In our test it raised fewer false alerts and used less memory.
Gemma 4 12B: about 7.2 GB. It caught slightly more of the test situations, with more false alerts.
Station only runs these exact, verified files. Every download and every file you already have is checked against its published SHA-256 checksum before use.
What your computer needs
A desktop Station on Windows (x64), macOS (Intel or Apple Silicon) or Linux (x64 or ARM64). The Android and iPhone apps use cloud providers.
16 GB of memory or more. An NVIDIA GPU with 8 GB of video memory or more, or a Mac with Apple Silicon, makes each check several times faster. On the processor alone a model works, but checks take much longer, which suits one or two cameras that analyse on movement.
About 8 GB of free disk space for the model, plus up to 2 GB while the NVIDIA runtime installs.
Setup shows what Station found on your computer and warns you if something looks short, but it never blocks you: the image-analysis test at the end shows whether the model works.
Speed and capacity
On a laptop with an NVIDIA RTX 4080 (12 GB), a check of 20 frames took about 4 seconds, and one check runs at a time. Station queues up to four checks and keeps the model loaded between them.
How many cameras one computer can handle depends on its GPU, how often each camera analyses and how many Events it watches for. Movement-based analysis needs far fewer checks than continuous analysis.
Costs
A local model has no AI provider charge: token usage is still recorded, at $0. Your Agentinosaurus plan and camera slots are billed as usual, and the computer’s electricity and hardware are yours.
Privacy and safety
Model downloads start only after you allow local setup on the Station itself, from its menu. Our servers can’t start a download or run a program on your computer on their own.
The model runs on your computer only, on a private local port with a key that changes each start. Station never falls back to a cloud provider: if the model can’t run, the camera reports a problem instead.
Station looks for existing model files in Downloads, LM Studio and the Hugging Face cache, and reports only which model it found, never the folder.
Questions & answers
Do camera frames leave my computer with a local model?
Not for detection. Frames are analysed on the Station computer. Answers, incident details and device health still reach your workspace. Camera Chat is separate and uses OpenAI.
Can I use a different model or my own files?
Only the supported Qwen 3.5 9B and Gemma 4 12B files. If you already downloaded them, for example with LM Studio, Station uses them where they are after checking them.
What happens if the computer restarts?
Station loads the model again in the background after it starts, so cameras resume without you doing anything.
$AGSAUR · Solana · x402
The Agents in this guide are metered in $AGSAUR.
Every observation, question and webhook an Agent runs is settled in $AGSAUR over x402 on Solana — no cards, no subscription, no invoice. Station operators earn the same token for keeping the network awake. Launching soon.
Launching on Solana — CA drops with the token