QwenReleased on Apr 16, 2026

Qwen3.6-35B-A3B: Benchmarks, Pricing & Context Window

Qwen3.6-35B-A3B is a language model from Qwen, released in April 2026, with multimodal input.

Qwen3.6-35B-A3B is the first open-weight variant of the Qwen3.6 series, a multimodal Mixture-of-Experts model with 35B total parameters and 3B activated. It pairs a vision encoder with a hybrid 40-layer language model that interleaves

Qwen3.6-35B-A3B API

API access coming soon

Qwen3.6-35B-A3B will be available through our gateway shortly.

Qwen3.6-35B-A3B examples

Recent arena outputs from Qwen3.6-35B-A3B, picked from the highest-ranked matchups.

Qwen3.6-35B-A3B license

Qwen3.6-35B-A3B is released under the Apache 2.0 license, which permits commercial use, has 35.0B parameters.

License
Apache 2.0
Commercial use allowed
Parameters
35.0B

Apache License 2.0 - allows commercial use

FAQ

Common questions about Qwen3.6-35B-A3B.

What is the Qwen3.6-35B-A3B release date?

Qwen3.6-35B-A3B was released on April 16, 2026 by Qwen.

Who created Qwen3.6-35B-A3B?

Qwen3.6-35B-A3B was created by Qwen.

How many parameters does Qwen3.6-35B-A3B have?

Qwen3.6-35B-A3B has 35.0 billion parameters.

What is the license for Qwen3.6-35B-A3B?

Qwen3.6-35B-A3B is released under the Apache 2.0 license. This is an open-source/open-weight license.

Is Qwen3.6-35B-A3B multimodal?

Yes, Qwen3.6-35B-A3B is a multimodal model that can process both text and images as input.