Unverified50% confidenceFactExact time
DeepSeek's Pro model has an activation ratio of approximately 3% (49B activated / 1.6T total parameters), which is a typical characteristic of MoE architecture.
1
Sources
50%
Confidence
Long-term
Relevance
9/21/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe DeepSeek series of models adopts a MoE architecture, activating only 10%–20% of total parameters during each inference.76% similarVerifiedDeepSeek-V3 adopts a Mixture of Experts (MoE) architecture with a total parameter count of 671 billion, but only approximately 37 billion parameters are activated per inference.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/938985API
curl https://kongchang.com/api/v1/knowledge/claims/938985MCP
get_claim(id=938985)