Skip to content

Display tokens per second in the chat #7563

Description

@Andy92j

It would be very helpful to see how fast the AI responds i mean how many tokens per second (T/s) it processes. For example, in LM Studio, you can see this displayed under each message while the AI is generating a response. This would be extremely useful for tracking performance when adjusting settings.

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions