Qwen 3.6 27B

• 🆕 Dense 27B native vision-language model from Alibaba's Qwen team
• 👁️ Natively handles text, image, and video inputs
• 📏 256K-token native context window
• 🔧 Hybrid Gated DeltaNet plus full attention; FP8 checkpoint available
• 🧠 Adds "Thinking Preservation" to reuse reasoning across agent turns
• 🎯 Improved agentic coding, STEM reasoning, spatial intelligence, OCR
• 💬 Supports thinking and non-thinking modes, plus tool calling
• 🏢 Open-weight, deployable on vLLM, SGLang, Transformers

Alibaba

Alibaba Group is a Chinese multinational technology company founded in 1999 and headquartered in Hangzhou, Zhejiang. Originally built around e-commerce and cloud computing, Alibaba has become one of the most prolific contributors to open-weight AI research,…

Qwen 3.6 27B is the dense, natively multimodal flagship of Alibaba's Qwen3.6 family, released in April 2026. It directly builds on the dense Qwen3.5-27B, sharing the same hybrid attention design that mixes Gated DeltaNet linear attention with traditional full attention to cut KV-cache cost on long contexts. The model is a causal language model with an integrated vision encoder, processing text, image, and video inputs through both pre-training and post-training stages.

Compared with its predecessor, Qwen describes key gains in agentic coding, STEM reasoning, and vision tasks such as spatial intelligence, object localization, and document OCR. On the benchmarks Alibaba reports using its own internal agent scaffold, Qwen3.6-27B reaches 77.2% on SWE-bench Verified and 59.3 on Terminal-Bench 2.0, figures the team says exceed both Qwen3.5-27B and the much larger MoE Qwen 3.5 397B (397B total, 17B active).

A notable new feature is "Thinking Preservation," which retains reasoning traces across conversation history to reduce redundant token generation and improve KV-cache efficiency in multi-turn agent loops. Native context is 262,144 tokens.

Within the broader family, Qwen 3.6 27B sits alongside the sparse Qwen 3.6 35B A3B FP8 and Qwen 3.6 Plus, and the earlier Qwen 3.5 9B and Qwen 3.5 35B A3B. It ships as both BF16 and fine-grained FP8 checkpoints, supporting vLLM, SGLang, and Hugging Face Transformers.