Unverified50% confidenceFactExact time
混元3是混合专家模型（MoE），总参数量为295B，激活参数约21B
1
Sources
50%
Confidence
Long-term
Relevance
7/10/2026
First Seen
Sources
Related Claims
Unverified千问3.6的35B MOE模型每次只激活其中3B的参数80% 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.79% 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3B76% similarUnverifiedXiaomi MiMo adopts a Mixture-of-Experts (MoE) architecture with a total parameter count of 24.6B, activating only approximately 5.3B parameters per inference.76% similarUnverifiedQwen3's 235B-parameter MoE flagship model approaches or surpasses closed-source top-tier models on multiple authoritative benchmarks.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/465607API
curl https://kongchang.com/api/v1/knowledge/claims/465607MCP
get_claim(id=465607)