Qwen 3.6 35B A3B

About this model

Qwen 3.6 35B A3B is a 35 B parameter mixture‑of‑experts vision‑language model with a gated delta network architecture and a vision encoder. It supports a native context window of 262 K tokens (extendable to over 1 M tokens) and can be used for image‑text‑to‑text tasks. The model achieves strong performance on benchmarks, scoring 85.2 % on MMLU‑Pro, 81.4 % on MMMU, and 85.3 % on RealWorldQA. It is released under the Apache 2.0 license.

Technical specifications

Capabilities

Input modalities

Output modalities

Reasoning

Hybrid Default on

Knowledge horizon