Please add a “Unload after Run” feature to the ☁️API LLM general link node

[Djanghost]

Is your feature request related to a problem? Please describe.
When using Ollama, the model remains loaded and takes up a lot of memory.

Describe the solution you'd like
Add an “Unload after Run” feature to the ☁️API LLM general link node, like other similar LLM nodes.

Describe alternatives you've considered
The only solution for unloading the model and emptying memory for the moment is to close ollama just after the node has given the result.

Additional context

For example:

[heshengtao]

There is a node called "clear model". Turn on the "is ollama" option on this node, and insert this node at any point in the workflow where you want to unload the model. When the workflow reaches this node, it will exit the ollama model.

[Djanghost]

Thanks for your answer, will try this for sure.