Unverified50% confidenceFactExact time
Qwen3-235B的MoE版本实际激活参数仅约22B
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/25/2026
First Seen
Valid until: 11/23/2026
Sources
Related Entities
Related Claims
VerifiedQwen3-235B has a total parameter count of 235 billion, adopts a MoE architecture, and activates approximately 22B parameters during each forward inference pass.79% similarUnverifiedQwen3旗舰版（235B）的参数量仅为DeepSeek旗舰版（671B）的三分之一左右78% similarUnverifiedSome community users have speculated that Qwen may skip the 35B specification and directly release a MoE model at the 122B scale.78% similarUnverifiedThe 14B MoE model is derived by compressing the Qwen3.6 35B MoE, reducing total parameters from 35B to 14B, while the active parameters per forward pass remain at 3B, fully consistent with the original 35B74% similarUnverifiedAlibaba open-sourced Qwen3.5, a Mixture of Experts model with 397B total parameters and only 17B parameters activated.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/798069API
curl https://kongchang.com/api/v1/knowledge/claims/798069MCP
get_claim(id=798069)