Qwen 3.6 27B

At a glance

What Qwen 3.6 27B does

Tool use, Streaming, Structured output, Dense 27B (no MoE), Agentic coding, Function calling, Apache 2.0, Beats 397B MoE on agentic benchmarks, Self-hostable

Best for

Single-GPU agentic coding (fits on 1x H100), workstation deployment, beats much larger MoE models on agentic tasks, Apache 2.0 commercial use

Works well with

Conflicts & caveats

• Trae's built-in model menu may not include Qwen 3.6 27B — Trae primarily ships with Claude/GPT/Gemini/DeepSeek.
• Google Antigravity is built around Gemini 3 Pro; Claude and recent GPT-5 models also work, but Qwen 3.6 27B is not in the supported model list.
• Kiro's spec mode is tuned for Claude models — Qwen 3.6 27B may work but spec-driven flows are best with Claude.
• Cursor's built-in model menu may not include Qwen 3.6 27B — verify it's available in your Cursor model picker.
• OpenAI Codex (VS Code) is tied to OpenAI's GPT-5.1 Codex family — Qwen 3.6 27B is not selectable inside this integration.
• Gemini CLI is locked to Google Gemini models — your LLM is Qwen 3.6 27B.
• Privacy conflict: Self-hosted Qwen 3.6 27B sends code to cloud @codebase (Cursor). Use local context (Continue indexing, ChromaDB, LanceDB, pgvector, Vespa self-hosted) for true privacy.
• Claude Code only works with Claude models — your LLM is Qwen 3.6 27B.
• Devin uses Cognition's proprietary model internally — your selected Qwen 3.6 27B will be ignored.
• OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected Qwen 3.6 27B will be ignored.
• Jules runs Gemini models internally — your selected Qwen 3.6 27B will be ignored.
• The Claude Code SDK is tuned for Claude models — Qwen 3.6 27B may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
• Lovable uses a fixed internal model — your selected Qwen 3.6 27B will be ignored.
• Replit Agent 3 uses its own model selection internally — your selected Qwen 3.6 27B will be ignored.