Qwen Console

Live decode—tok/s · streaming

TTFT—time to first token

Output—tokens this reply

Backend load—running / queued

✦

Ask anything

Pick a model, toggle Think or Fast, and go.

Throughput—tok/s · all models

Active—running requests

Pending—queued requests

Total calls—since start

Prefix cache—hit rate

Mean call—inference time

Model	GPU	Run	Wait	tok/s	KV	Cache	MTP

Model	Status	Engine	GPU	Endpoint (OpenAI /v1)	Ctx	Capabilities

Time	Model	Src	Status	Conn	Recv	Prompt	Out	Prefill	TTFT	tok/s	KV MB