FW-Qwen3.6-27B

Models available for use with Fireworks on Foundry deliver optimized, best-in-class performance on the Fireworks Inference Cloud. Fireworks on Foundry is a Non-Microsoft Product. The following terms apply to a Customer's use of Fireworks on Foundry: When you use Fireworks on Foundry, data is shared between Microsoft and Fireworks AI, Customer Data will be sent outside of Microsoft systems, Customer Data will not be processed pursuant to any Foundry data residency documentation, and different compliance and data handling rules will apply. See Trust Center - Fireworks AI for details. Customers are responsible for evaluating whether data sharing between Microsoft and Fireworks is appropriate for their organization's compliance requirements.

About this model

Qwen3.6-27B is a 27B-parameter dense causal language model from Alibaba's Qwen3.6 family. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive experience. Key upgrades include substantial improvements in agentic coding (handling frontend workflows and repository-level reasoning with greater fluency and precision) and a new thinking preservation option to retain reasoning context from historical messages. The model supports seamless switching between thinking and non-thinking modes, strong reasoning, coding, and agent capabilities, multilingual support, and a native 262,144-token context window.

Key model capabilities

• 27B-parameter dense transformer architecture
• Seamless switching between thinking and non-thinking modes
• Enhanced agentic coding with frontend workflows and repository-level reasoning
• Thinking preservation for retaining reasoning context from historical messages
• Tool calling and function calling support
• 262,144-token native context window