Question 1

How large is the context window?

Accepted Answer

262,144 tokens natively, per both config.json and the model card. The card states it is extensible up to 1,010,000 tokens with appropriate serving configuration; treat the native 262K as the dependable planning number.

Question 2

Is Qwen3.6-27B multimodal?

Accepted Answer

Yes. It is an image-text-to-text model with a vision encoder, and the model card demonstrates both image and video input through OpenAI-compatible messages. Output is text only.

Question 3

Does it emit thinking tokens?

Accepted Answer

By default, yes: responses begin with a ... block before the final answer. The card documents an instruct (non-thinking) mode for direct responses, and a new thinking-preservation option that carries reasoning context across turns in agent workflows.

Question 4

What sampling parameters should I use?

Accepted Answer

Per the model card: temperature 1.0, top_p 0.95, top_k 20, min_p 0 for general thinking-mode tasks; drop temperature to 0.6 for precise coding work such as WebDev; and temperature 0.7, top_p 0.80, top_k 20 with presence_penalty 1.5 for instruct mode.

Question 5

How do I call it from the OpenAI SDK?

Accepted Answer

Set base_url to https://llm.chutes.ai/v1, use your Chutes API key, and pass model Qwen/Qwen3.6-27B-TEE. Chat completions with streaming work as with any OpenAI-compatible endpoint.

Question 6

What does TEE mean for this chute?

Accepted Answer

The model runs inside a Trusted Execution Environment: attested confidential-compute hardware, so prompts and outputs are processed in protected memory. It is a serving property; the underlying weights are the Qwen3.6-27B FP8 build.

Question 7

Can I use it commercially?

Accepted Answer

Yes. The upstream repository is Apache-2.0 licensed, which allows commercial use, modification, and redistribution. Endpoint usage is billed through your Chutes account, separately from the model license.

Question 8

How good is it at coding, really?

Accepted Answer

The model card reports 77.2 on SWE-bench Verified, 53.5 on SWE-bench Pro, 71.3 on SWE-bench Multilingual, and 59.3 on Terminal-Bench 2.0. The release explicitly targets agentic coding, frontend workflows, and repository-level reasoning.

Qwen3.6 27B

Sign in to use the playground

Qwen3.6 27B

Sign in to use the playground