Unverified50% confidenceFactExact time
Qwen3.8 Flash Next has 125 billion total parameters, with only approximately 6 billion parameters activated per token during inference
1
Sources
50%
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 approximately 6B activated parameters.76% similarUnverifiedQwen系列有从15亿到720亿不等的多个参数规格75% similarUnverifiedQwen Coder adopts a Mixture of Experts (MoE) architecture with 480 billion total parameters, activating only 35 billion parameters during inference.74% similarUnverifiedTongyi Qianwen Qwen3-0.6B is a lightweight model with only 600 million parameters, suitable for local environment deployment and debugging.73% similarUnverifiedThe activated parameter count of Qwen3.8 Flash is approximately one-third that of GLM.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/867072API
curl https://kongchang.com/api/v1/knowledge/claims/867072MCP
get_claim(id=867072)