All cards
Data source
active
local-only
data-ollama
Local Ollama LLM runtime on Beacon loopback 11434, one small model loaded
Endpoint
http://127.0.0.1:11434Packaging
systemd
Owner
operator
Version
v1
Updated
2026-06-26
Health check
curl -fsS http://127.0.0.1:11434/api/tagsPurpose
Local LLM inference runtime. One small model loaded. Unclear which downstream services consume it. Handoff flagged: keep if a service uses it, decommission if experimental to free RAM.
Capabilities 2
llm-inference
Local LLM inference via Ollama API
model-registry
Model registry, currently one small model
History 1
Createdai2026-06-26Card created by AI session (audit 2786).
Createdai2026-06-26
Card created by AI session (audit 2786).