LLM Service – test page

Server

API key (stored in this browser only)

Status…

Model…

Waiting / running…

Context (num_ctx)–

Instructions (system prompt) JSON schema of the answer (optional – leave empty for plain text)

Temperature Max output tokens

Input URLs (one per line, optional – the server downloads them)

Status–

Elapsed (total)–

Waited in queue–

Model load–

Prompt processing–

Generation–

Tokens in / out–

Tokens/s (output)–

When	What	Status	Total	Load	Tok/s	Out tok