Questions people ask first.

For one machine and one laptop, that works, and Ollama still runs underneath Qadenza if you use it. Qadenza is the part you'd otherwise build yourself on top:

• No VPN client on every device. The relay is plain HTTPS, so a browser, a phone, or any OpenAI client reaches your models.
• Every machine in one dashboard. GPU temps, VRAM and power, and loading or pulling models, without SSH.
• Fit, before you download. Each model is checked against the memory that's free right now.
• llama.cpp next to Ollama, with a model split across every GPU in the box.
• A coding agent in VS Code, MCP both ways, and API tokens you can revoke.

When you reach a machine remotely, yes, in transit and encrypted. We don't store them or use them for anything. Air-gapped, they never touch us. What the relay sees.

Any Mac, Linux or Windows machine you can install the agent on. Qadenza tells you which models fit its memory before you download one. More VRAM means bigger models; CPU-only machines run small ones.

Anything in Ollama's library, and GGUF models from Hugging Face or ModelScope on llama.cpp, including sharded ones. Safetensors models can be converted to GGUF on the machine.

Yes. Anything that takes a custom OpenAI base URL works, with a token from Settings. For agents that speak MCP, claude mcp add qadenza -- qadenza mcp adds your models as tools.

Yes. Point the agent at your own relay with qadenza config set relay-url. For a deployment with no internet at all, see air-gapped.

Yes. We deploy the relay, API and dashboard inside your network, and deliver models and updates offline. Air-gapped deployments.

Request an invite. We let people in in small batches and email you when it's your turn. The install command needs an invited account.