Unverified50% confidenceFactExact time
4B表示模型参数量为40亿，属于小型语言模型（SLM）范畴
1
Sources
50%
Confidence
Long-term
Relevance
8/21/2026
First Seen
Sources
Related Claims
VerifiedGLM-4.6 adopts a Mixture of Experts (MoE) architecture, with a total parameter count of 355 billion, activating approximately 32 billion parameters during inference.67% 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.66% similarUnverified阿里巴巴发布的升级版通义千问模型参数规模达到 2.4 万亿，略小于 Kimi K365% 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.65% similarUnverified2.4万亿参数模型在BF16精度下考虑KV Cache和激活值后实际约需1.4-1.5TB显存65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/783975API
curl https://kongchang.com/api/v1/knowledge/claims/783975MCP
get_claim(id=783975)