Qwen3.6-35B-A3B
Open multimodal model for coding, agents, and long-context tasks
...The model emphasizes stability, responsiveness, and practical developer productivity, with major improvements in agentic coding, frontend generation, and repository-level reasoning. A notable addition is thinking preservation, which allows the model to retain reasoning context from earlier messages, improving iterative work and reducing redundant computation. Architecturally, it uses a Mixture-of-Experts design with 35B total parameters and 3B active, supports a native 262K-token context window, and can be extended to about 1M tokens with YaRN. ...