Skip to content
Erebrosdocs

Qwen

Qwen is the Chat engine for Qwen models on the Alibaba Model Studio cloud plan, in Chat — /chat?engine=qwen.

Qwen — Erebros

What it does

Section titled “What it does”

A dedicated engine (text in, text out) talking to the Model Studio chat API, with the shared Chat / History / Workspace tabs and Settings panel. This is the cloud Qwen — not Ollama; a Qwen model you pull locally appears under the Local engine instead. It is also distinct from the Qwen Code engine (/chat?engine=qwen-cli), which uses the agentic qwen CLI with real file tools.

Key actions

Section titled “Key actions”
  • Chat — send prompts, resume past threads, browse Sessions, read the Telemetry row.

Setup

Section titled “Setup”

Requires the Model Studio cloud plan key QWEN_CLOUD_KEY in .env.local (from Alibaba Model Studio), then restart the server. One plan feeds both the Qwen and DeepSeek engines. Without it, this engine reads “no cloud plan” — pull a Qwen model into Ollama and use the Local engine instead:

Terminal window
ollama pull qwen2.5-coder:7b

Tips

Section titled “Tips”
  • Do not confuse this engine with the Qwen Code agent CLI.

See also

Section titled “See also”