Verified70% confidenceOpinionExact time
The approximately 20:1 ratio between Qwen3 Next Flash's 125 billion total parameters and 6 billion activated parameters represents a fairly aggressive sparsity design.
4
Sources
70%
Confidence
Medium-term (~90 days)
Relevance
9/6/2026
First Seen
Valid until: 12/5/2026
Sources
Related Entities
Related Claims
UnverifiedQwen3.8-Flash-Next has a total parameter count of 125B with approximately 6B activated parameters, and belongs to the sparse MoE architecture.77% similarUnverifiedQwen 3.8 Flash has a parameter count of 180B, which is half that of GLM 5.3 Flash (320B).76% similarUnverifiedAlibaba's Tongyi Qianwen officially released Qwen3.8-Flash-Next (Qianwen 308 Flash NEX), with total parameters as high as 181.5B.74% similarUnverifiedV4.1 Flash activates only 8 billion parameters during the input stage and 16 billion parameters during the output stage.72% similarPartially VerifiedThe 4-bit quantized version (Q4K XL) of Qwen3 Next Flash is approximately 111 GB.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/863374API
curl https://kongchang.com/api/v1/knowledge/claims/863374MCP
get_claim(id=863374)