Local model operator

Paddock documentation

Install the current alpha, understand the trust boundary, and bring one local model online.

Public alpha · Linux x86-64

Start with the support boundary

The current public channel is an honest Linux x86-64 alpha. Review the release evidence before changing a host.

llama.cpp is the supported production runtime.
Current real-runtime evidence covers one Linux amd64 CUDA RTX 5090 host.
CPU, ROCm, Vulkan, arm64, and experimental vLLM paths are not implied by the alpha label.

The check command verifies the current download without modifying the host. Run it before installation.

bash <(curl -fsSL https://get.kinra.ai/paddock/install.sh) --check
bash <(curl -fsSL https://get.kinra.ai/paddock/install.sh)

Paddock detects the host, checks out its known-good llama.cpp revision, and builds the appropriate backend.

sudo -u paddock PADDOCK_ROOT=/var/lib/paddock \
  /usr/local/bin/paddock install-llamacpp

A pull stages, validates, and atomically registers the selected GGUF artifact set.

sudo -u paddock PADDOCK_ROOT=/var/lib/paddock \
  /usr/local/bin/paddock pull unsloth/Qwen3-30B-GGUF:Q4_K_M

Start the service, then use the loopback dashboard and API.

sudo systemctl enable --now paddock.service
# dashboard and API
http://localhost:5467

Maintained depth