Qwen 3 235B A22B

Flagship Qwen3 MoE

This is the largest-capacity Qwen3 release in the current line, intended as the top open model in the family.

Sparse activation at scale

The model keeps 235B total parameters but only 22B activated per token, which is the core reason to deploy it as an MoE rather than a dense frontier-scale model.

Reasoning and agent focus

Qwen still frames the flagship around reasoning, instruction following, and agent-style workflows rather than only benchmark scale.

MoE family branch

Qwen3 includes dedicated MoE models alongside the dense line, keeping the same user-facing thinking/non-thinking framing while changing the serving geometry materially.

Sparse activation

The MoE releases expose total and activated parameter counts separately, which is the key deployment distinction versus the dense Qwen3 models.

Long-context packaging

The base MoE releases are published with 32K native context and 131K support with YaRN, while the 2507 update is packaged at 256K native context.

Reasoning with lower active compute

The MoE line is for users who want larger total capacity without paying dense-model active compute per token.

Agent and tool use

Qwen still positions the MoE branch around agent workflows, tool calling, and mixed reasoning/general dialogue use.

Large multilingual serving

Useful when you want very large-capacity multilingual serving without moving to a purely dense 70B+ model.