Unverified60% confidenceFactTime unknown
Qwen Coder adopts a Mixture of Experts (MoE) architecture with 480 billion total parameters, activating only 35 billion parameters during inference.
2
Sources
60%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Qwen Code CLI实测：阿里开源AI编码代理安装配置全指南
bilibiliAI-seeker
Related Entities
Related Claims
Partially VerifiedBoth Qwen 3 Max and DeepSeek-V3 adopt the MoE architecture with total parameter counts reaching hundreds of billions, but the parameters actually activated during inference are only a small fraction of the total.78% similarVerifiedGemma 4's 26B MoE model uses a Mixture of Experts architecture, with 26 billion total parameters but only approximately 4 billion parameters active at any given moment.75% similarVerifiedHy3 adopts a Mixture of Experts (MoE) architecture with a total parameter count of 295 billion (295B), activating only 21 billion (21B) parameters per inference.74% similarUnverifiedQwen3.8 Flash Next has 125 billion total parameters, with only approximately 6 billion parameters activated per token during inference74% 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3B74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/23558API
curl https://kongchang.com/api/v1/knowledge/claims/23558MCP
get_claim(id=23558)