Expired60% confidenceFactTime unknown
The Gemma 4 26B MOE version has a total parameter count of 25.2B, but only approximately 3.8B parameters are activated during inference.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
Gemma 4 Complete Guide: The Apache 2.0 Open-Source Agent Powerhouse
bilibiliAI全文总结
Related Claims
UnverifiedGemma's parameter scale ranges from 2B to 27B.79% similarUnverified千问3.6的35B MOE模型每次只激活其中3B的参数75% 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% 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.74% similarUnverified千问三235B MoE总参数量2350亿，但每次推理实际激活的参数约22B73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/57144API
curl https://kongchang.com/api/v1/knowledge/claims/57144MCP
get_claim(id=57144)