Qwen3.6-35B-A3B is Qwen's sparse Mixture-of-Experts multimodal model: 35B total parameters with 3B active per token, text and image input, a 262K-token native context extensible to 1M, thinking and non-thinking modes, and strong agentic coding, released under Apache 2.0.
Qwen3.6-35B-A3B is a 40-layer Mixture-of-Experts model on the Qwen3.5 hybrid architecture: 10 blocks that each stack three Gated DeltaNet linear-attention layers ahead of one gated full-attention layer, with 256 experts per MoE layer and 8 routed plus 1 shared expert active per token, so only about 3B of its 35B parameters fire on each step. A vision encoder handles image input. Context is 262,144 tokens natively and extends to 1,010,000 with YaRN. It thinks by default, can be switched to a non-thinking mode, and supports preserve_thinking to carry reasoning across turns in agentic workflows, plus a multi-token-prediction head for speculative decoding.
It was the first open-weight Qwen3.6 model. Qwen recommends keeping at least 128K tokens of context to preserve thinking and enabling YaRN only when inputs exceed the native window. Weights are released under the Apache 2.0 license. Full details are in Qwen's announcement and the model card.
A Dedicated Endpoint is your own deployment of Qwen3.6 35B A3B, on an inference stack that Modal tunes and autoscales. Bring fine-tuned weights if you have them. Compute is billed by the second, and only while it runs.
modal endpoint create --model Qwen/Qwen3.6-35B-A3B