Expired80% confidenceFactExact time
Qwen3-235B has a total parameter count of 235 billion, adopts a MoE architecture, and activates approximately 22B parameters during each forward inference pass.
8
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
7/21/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/19/2026(expired)
Sources
Related Claims
Unverified千问三235B MoE总参数量2350亿，但每次推理实际激活的参数约22B84% similarPartially VerifiedTongyi Qianwen released the Qwen 3.8 Max model, with a parameter scale as high as 2.4 trillion.80% similarVerifiedQwen3.6 35B-A3B是混合专家架构（MoE），总参数量35B，每次推理实际激活参数量约3B80% similarUnverifiedQwen Coder adopts a Mixture of Experts (MoE) architecture with 480 billion total parameters, activating only 35 billion parameters during inference.77% similarUnverifiedHy3 adopts a Mixture of Experts (MoE) architecture with a total parameter count of 295 billion (295B), activating only 21 billion (21B) parameters per inference.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/579762API
curl https://kongchang.com/api/v1/knowledge/claims/579762MCP
get_claim(id=579762)