Qwen 3.6 27B

Model ID: vllm/release/qwen3.6-27b Qwen (Alibaba) Experimental

EU AI Act

Attribute	Value
Classification	GPAI (General-Purpose AI Model)
Risk class	Limited Risk (Article 52)
Transparency obligation	Yes
noris role	Deployer

As a GPAI model, this model falls within the scope of EU AI Act transparency obligations. noris acts as the deployer and ensures the required information is made available pursuant to Article 53.

Technical Specifications

Property	Value
Model name	Qwen 3.6 27B
Provider	Qwen (Alibaba)
Model ID	vllm/release/qwen3.6-27b
Parameters	27B (dense)
Architecture	Hybrid (Gated DeltaNet + Gated Attention)
Context length	262,144 (ext. 1,010,000 via YaRN)
Modalities	Text + image (multimodal/vision)
License	Apache 2.0

Recommended Use Cases

• Agentic coding (SWE-bench 77.2%)
• Frontend workflows
• Repository-level reasoning
• Thinking mode
• Vision/image analysis

Known Limitations

Caution

• Thinking mode enabled by default (generates extra tokens): enabled thinking mode increases token consumption and latency.
• Experimental tier: this model may be deprecated on short notice.
• Primarily EN/ZH: performance is mainly optimized for English and Chinese.

Risk Assessment (EU AI Act)

Risk Factor	Category	Level
Open source (Apache 2.0)	Misuse potential	Low
Multimodal	Image input / deepfake potential	Medium
Experimental tier	Deprecation notice	Flagged
Environmental impact	Model size (27B dense)	Medium

Training Data & Sustainability

Training data: not fully publicly documented.

Sustainability:

Metric	Value
CO₂	Medium (27B dense)
Optimization	Hybrid architecture (Gated DeltaNet) for efficient long contexts

Original Sources

• HuggingFace: https://huggingface.co/Qwen/Qwen3.6-27B
• License: Apache 2.0

Model card created on July 2, 2026. This model card serves EU AI Act transparency purposes (Regulation (EU) 2024/1689). The information is based on publicly available data from the model provider.