Unverified50% confidenceFactExact time
Agent A1 是一个350亿参数的MoE模型，每次推理仅激活约30亿参数
1
Sources
50%
Confidence
Long-term
Relevance
7/22/2026
First Seen
Sources
Related Claims
UnverifiedHy3 adopts a Mixture of Experts (MoE) architecture with a total parameter count of 295 billion (295B), activating only 21 billion (21B) parameters per inference.73% similarUnverifiedOn the Arena AI leaderboard, Gemma 4's 31-billion-parameter model ranks third among all open-source models, while the 26.1-billion-parameter version ranks sixth.72% 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.72% similarUnverified千问3.6的35B MOE模型每次只激活其中3B的参数72% similarVerifiedGLM-4.6 adopts a Mixture of Experts (MoE) architecture, with a total parameter count of 355 billion, activating approximately 32 billion parameters during inference.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/593881API
curl https://kongchang.com/api/v1/knowledge/claims/593881MCP
get_claim(id=593881)