Unverified60% confidenceFactExact time
Kimi K3's 2.8 trillion parameter scale surpasses the previously largest open-weight model, DeepSeek-V3, which had 671 billion parameters.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/19/2026
First Seen
Valid until: 10/17/2026
Sources
Related Claims
UnverifiedKimi K3 has a parameter scale of approximately 2.8 trillion and was released before Qwen3.8.82% similarUnverifiedKimi expanded from K2's 1 trillion parameters to K3's 2.8 trillion parameters.82% similarUnverifiedKimi K3 is a 2.8T-parameter multimodal LatentMoE model that uses 896 experts with top-16 routing and performs routing computation in a 3584-dimensional latent space.76% similarVerifiedKimi K2.6 adopts a Mixture of Experts (MoE) architecture, with a total parameter count at the trillion level and only 32B parameters actually activated.75% similarUnverifiedKimi K3于7月16日发布并接入Kimi Code，采用2.8万亿参数规模，最高支持100万Token上下文和原生视觉理解74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/563672API
curl https://kongchang.com/api/v1/knowledge/claims/563672MCP
get_claim(id=563672)