Unverified50% confidenceFactExact time
MiMo V2.6 Pro's total parameters are approximately half those of Kimi K3, but the activated parameters are on the same order of magnitude.
1
Sources
50%
Confidence
Long-term
Relevance
9/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedXiaomi MiMo adopts a Mixture-of-Experts (MoE) architecture with a total parameter count of 24.6B, activating only approximately 5.3B parameters per inference.73% similarUnverifiedKimi's parameter count grew from 1T in K2 to 2.8T in K3.64% similarUnverified千问3.6的35B MOE模型每次只激活其中3B的参数63% similarUnverifiedKimi expanded from K2's 1 trillion parameters to K3's 2.8 trillion parameters.62% similarUnverifiedThe specific benchmark results of MiMo-V2.6 and its horizontal comparison with similar open-source omnimodal models (such as the Qwen-VL series) remain to be tested.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/941004API
curl https://kongchang.com/api/v1/knowledge/claims/941004MCP
get_claim(id=941004)