Ollama Monitor

Talking to

–

Last clientnone yet

–

Loaded modelnone

Context–

In memory–

–%

Load 1 / 5 / 15 min–

Cores–

–GB

Total–

Available–

–tok/s

Requests in flight0

Tokens streaming0

Elapsed–

–avg tok/s

Requests0

Generated tokens0

Prompt tokens0

Time	Client	Endpoint	Model	Prompt tok	Gen tok	Prompt tok/s	Gen tok/s	Total s

No requests recorded yet.

route every request to the active model (ignore what the client asks for) let the model think before answering (slower; off = fast direct answers)

Active–

Status–

Model	Params	Quant	Size	State

Downloads run on the server in the background; the model is imported with a 64K context and appears in the switcher when done.

streams a short reply through the same endpoint VS Code uses