Unverified60% confidenceFactTime unknown
M2.5 adopts a Mixture of Experts (MoE) architecture, where only 10B parameters are actually involved in computation during each inference, while the total parameter count may far exceed 10B.
2
Sources
60%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe project adopts a sparse mixture-of-experts (MoE) architecture, in which only about 9B parameters are activated per token out of 74B total parameters, an activation ratio of about 12%.74% similarVerifiedThe Mixture of Experts (MoE) architecture activates only approximately 10%–30% of total parameters during inference, significantly reducing FLOPs and GPU memory usage per inference74% similarUnverifiedGoogle DeepMind研究表明，涌现能力表现为非线性的相变特征，模型参数量从10B增长到100B过程中某些复杂推理能力会突然跃升70% similarUnverifiedMoE架构中，一个标称800亿参数的模型每次推理时可能只激活约200亿参数，VRAM占用大幅降低70% similarUnverifiedPapers on the BitNet b1.58 series published by Microsoft Research show that a 1.58-bit model with the same parameter count can achieve perplexity close to that of a full-precision model70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/13431API
curl https://kongchang.com/api/v1/knowledge/claims/13431MCP
get_claim(id=13431)