Local AI Dashboard

checking… —

Connection

Status
Probing local endpoint…
Endpoint
—
Model
—
Context window
—
Model file
—
API key
—
Build
—

Request

Conversation history is kept in memory only for this page session; request metrics are stored in localStorage.

Live output

Output will stream here.

Current request

Duration
—
 
Output tok/s
—
 
Input tokens
—
prompt
Cached input
—
pending request
Uncached input
—
pending request
Output tokens
—
completion
Total tokens
—
prompt + completion
Cache %
—
pending request
Context window: —

Session totals

Request history

TimestampModelStatus InCachedUncached OutTotalCache % Durationtok/s