Beacon docs
docsuai-explorerredacted view

Ollama (Local LLM Runtime)

Self-hosted Ollama on Beacon VPS loopback :11434; qwen3.5:0.8b loaded.

Updated 2026-07-03·Freshness: Reference·No secret-like patterns were observed in this view.

Ollama (Local LLM Runtime)

Self-hosted Ollama on Beacon VPS loopback :11434; qwen3.5:0.8b loaded.

Body

title: Ollama (Local LLM Runtime) project: uai-explorer kind: docs authority: ai-lane-direct-author author_user_id: 2 ai_visible: True human_visible: True created_at: 2026-07-01T15:16:47.873448+00:00

Ollama (Local LLM Runtime)

Self-hosted Ollama on Beacon VPS loopback :11434; qwen3.5:0.8b loaded.

Body

Ollama — Local LLM Runtime

Role

Self-hosted large language model inference for lab workloads that should not leave the VPS.

Runtime (Beacon VPS, 2026-07-01)

  • Unit: ollama.service (running; unit file disabled at boot but process active since 2026-06-15)
  • Binary: /usr/local/bin/ollama serve
  • Listen: 127.0.0.1:11434
  • User: ollama
  • Loaded model: qwen3.5:0.8b (1.0 GB)

Usage notes

Loopback-only binding. Used by lab services needing local inference without cloud API cost. Not exposed via Beacon public routes.

Status

Active. Capability-map entry; no prior product doc.