Tongyi Qwen3.6-35B-A3B is an open-source application that focuses on low-cost agent programming and multimodal reasoning.

Alibaba's Tongyi Lab has open-sourced the sparse MoE model Qwen3.6-35B-A3B, boasting 35 billion total parameters but only 3 billion parameters activated during inference. It claims to significantly outperform its predecessor, Qwen3.5-35B-A3B, on programming benchmarks such as SWE-bench and Terminal-Bench, and is comparable to larger, denser models like Qwen3.5-27B and Gemma-31B. The model natively supports text-image, multimodal, and spatial intelligence, achieving a RefCOCO score of 92.0 and an ODINW13 score of 50.8. It is already open-sourced on Hugging Face and ModelScope, can be deployed locally, and is planned to be available through Alibaba Cloud's Bailian platform via an API compatible with OpenAI and Anthropic protocols, supporting integration with OpenAI.