ollama
| Version | 2026.144.1443 |
| Repo | superproject |
GPU-agnostic Ollama LLM inference server on port 11434
Installs the upstream Ollama binary (release tarball extracted to /usr,
no systemd) and runs ollama serve as a custom supervisord service that
listens on 0.0.0.0:11434. The binary auto-detects a GPU at runtime and
falls back to CPU inference, so the candy carries no CUDA dependency.
Pulled models persist under the ~/.ollama models volume. The running
service exposes the Ollama HTTP API (e.g. /api/tags) so any composing box
can serve and query local models.
Services
Section titled “Services”ollama
Acceptance plan
Section titled “Acceptance plan”This candy’s plan: — the runnable spec charly check executes against a live deployment. check: steps are idempotent probes; run: steps change state.
| Intent | Step |
|---|---|
run |
download=https://github.com/ollama/ollama/releases/latest/download/ollama-linux-amd64.tar.zst |
check |
the ollama binary is installed at /usr/bin/ollama |
check |
the running ollama service answers the model-tags API with HTTP 200 on port 11434 |
check |
the ollama CLI reports an “ollama version” string |
agent-check |
models pulled via ollama pull are stored under the ~/.ollama models volume and survive a service restart |