Unverified50% confidenceFactExact time
Ling-3.1-flash adopts a Mixture of Experts (MoE) architecture with a total parameter count of approximately 560 billion (~560B).
1
Sources
50%
Confidence
Long-term
Relevance
9/30/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedPangu 2.0 Flash adopts a MoE (Mixture of Experts) architecture with a parameter scale of 92B A6B (92B total parameters, 6B activated parameters).70% similarVerifiedDeepSeek V4 Flash uses a Mixture of Experts (MOE) architecture with a total parameter count exceeding 600 billion (600B+).68% similarUnverifiedQwen3.8 Flash Next additionally introduces an Ngram module with 51 billion parameters, resembling a massive local phrase memory table.68% similarUnverifiedDeepSeek-V4.1-Flash adopts a MoE (Mixture of Experts) backbone architecture with 552B parameters.67% similarUnverifiedAlibaba's Tongyi Qianwen officially released the Qwen3.8-Flash-Next (Qianwen 308 Flash NEX) model, with a total parameter count of 181.5B.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/962912API
curl https://kongchang.com/api/v1/knowledge/claims/962912MCP
get_claim(id=962912)