Get ClawBox — €749
Pre-configured with OpenClaw. Ships ready to use.
Prefer Hermes Agent? — €749
ClawBox Hermes Edition is the same hardware, shipped running Hermes Agent by Nous
Research instead of OpenClaw. Every specification on this page applies to both.
Specifications
What it’s good for
- A 24/7 personal assistant you message from Telegram or the web, with additional OpenClaw channels available for advanced setups when supported.
- Browser automation and everyday agent tasks.
- Running the preinstalled on-device model offline, or cloud AI providers (ClawBox AI, Claude, GPT, Gemini) when you want heavier reasoning.
The local model it ships with
ClawBox arrives with a local model already installed and running, so it works offline out of the box with nothing to download. It is Google Gemma 4 E2B (the QAT Q4_0 build) served by llama.cpp, and it appears in the provider and chat pickers as Gemma 4 (on-device). No API key, no account, no internet.
Measured on a Jetson Orin Nano 8GB against llama-server, the runtime the device
actually ships.
Why this build, and not a faster one. Four candidates from the same model
family were benchmarked on the device. Three were faster — one reached 34.7
tok/s — and all four scored 100% on strict JSON. This one ships because it is the
only one that reliably completes a two-step tool chain: look up the contact, then
send the mail. The others stop halfway and ask you for the address they were sent
to find. The larger E4B variant was rejected on the same grounds: 18.3 tok/s and
1.8 GB more memory for no gain in accuracy.
Installing Gemma 4 E2B from Ollama instead gives you a Q8_0 artifact of about
8.1 GB, which does not fit in 8 GB. The 3.1 GB above is the Q4_0 GGUF this device
ships with.
Bring your own local model (Ollama)
Measured on a production ClawBox with Ollama (warm runs,
num_predict=200, Ollama’s own
eval_rate; power and thermals from tegrastats over 176 samples): ~11.4 W average,
19.2 W peak, 61.8 °C peak, no throttling. Most people read at 5–8 tok/s, so the 1–4B
class generates faster than you can read. Full methodology:
We Benchmarked a Production ClawBox.
See full requirements and tiers in Hardware Requirements.
What to pair it with
ClawBox shines as an always-on gateway. For running large local models (70B–200B parameters) on-device, see ClawBox Workstation.In the box
- ClawBox unit (carbon-fiber case)
- USB-C power supply
- Quick-start insert
Set it up
Power on and run the guided wizard.