unload_model
Free VRAM when a model is no longer needed by unloading it from an Ollama provider, releasing memory for other tasks.
Instructions
Unload a model from VRAM on an ollama provider (frees memory immediately).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"model": "<model>"
},
"name": "unload_model"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | ||
| provider | No |