Qwen3.6-35B-A3B
Mixture-of-experts (MoE) model with 35B parameters, 3B active, for agentic coding; 73.4% on SWE-bench Verified.
Following the launch of Qwen3.6-Plus, we are excited to open-source Qwen3.6-35B-A3B — a sparse yet remarkably capable mixture-of-experts (MoE) model with 35 billion total parameters and only 3 billion active parameters.
Official source
Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to Allqwen.ai · published