Unverified50% confidenceFactExact time
LFM2.5-24B-A2B has 24 billion total parameters and uses an MoE architecture with 64 experts per block, Top-4 dynamic routing, and only 2.45 billion parameters activated per token.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedHy3 adopts a Mixture of Experts (MoE) architecture with a total parameter count of 295 billion (295B), activating only 21 billion (21B) parameters per inference.76% similarVerifiedQwen3-235B总参数量为2350亿，采用MoE架构，每次前向推理实际激活的参数量约22B75% 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% similarUnverifiedMoE模型中'35B'指总参数量，每个token只激活少量Expert（通常2-4个），实际计算量可能仅相当于6-7B的Dense模型73% 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/1029988API
curl https://kongchang.com/api/v1/knowledge/claims/1029988MCP
get_claim(id=1029988)