List Running Models
Query which model configurations are currently loaded and active in memory (RAM/VRAM).
GET /api/ps
Example
curl http://localhost:11434/api/ps
Response Payload
{
"models": [
{
"name": "gemma4:latest",
"model": "gemma4:latest",
"size": 4720938102,
"digest": "a8f8c7e9b23bb8f8c7e9b23bb8f8c7e9b23b",
"expires_at": "2026-06-05T14:55:00.90231Z",
"size_vram": 4720938102
}
]
}
If no models are loaded, the models array returns empty [].