1.2 KiB
1.2 KiB
| title | description | published | date | tags | editor | dateCreated |
|---|---|---|---|---|---|---|
| Ollama Model Management | Pulling, verifying, and managing models on the Gremlin stack | true | 2026-04-12T00:00:00.000Z | gremlin, ollama, models, runbook | markdown | 2026-04-12T00:00:00.000Z |
Ollama Model Management
Pull Required Models
Run on docker4 after any fresh deploy or after the Ollama container is recreated:
docker exec $(docker ps -qf name=gremlin_ollama) ollama pull llama3.2:3b
docker exec $(docker ps -qf name=gremlin_ollama) ollama pull qwen2.5-coder:7b
Verify Models Loaded
docker exec $(docker ps -qf name=gremlin_ollama) ollama list
Model Reference
| Model | Size | Pull Time (CPU) | Used By |
|---|---|---|---|
llama3.2:3b |
~2 GB | ~5 min | Kuma triage, Open WebUI |
qwen2.5-coder:7b |
~5 GB | ~15 min | Forgejo audit, Open WebUI |
Models Storage Path
/DockerVol/ollama — survives container restarts and redeployments.
⚠ Pull Before Workflows Run
n8n workflows fail silently if models aren't present. Ollama returns a model-not-found response but n8n may not surface this as an obvious error. Always pull models immediately after deploy before enabling workflows.