Unverified50% confidenceFactExact time
Qwen3.5-122B-A10B is a MoE architecture model with approximately 122B total parameters and approximately 10B activated parameters, activating only about 10 billion parameters per inference.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/7/2026
First Seen
Valid until: 12/6/2026
Sources
Related Entities
Related Claims
VerifiedQwen3-235B总参数量为2350亿，采用MoE架构，每次前向推理实际激活的参数量约22B75% similarUnverifiedIn the MoE architecture, the Mixtral 8x7B model has a total of 46.7B parameters, but only approximately 12.9B parameters (2 experts) are activated per token, making inference costs close to those of a 13B dense model while achieving performance comparable to the 70B level.74% similarPartially VerifiedBoth Qwen 3 Max and DeepSeek-V3 adopt the MoE architecture with total parameter counts reaching hundreds of billions, but the parameters actually activated during inference are only a small fraction of the total.72% similarVerifiedQwen3.6 35B-A3B是混合专家架构（MoE），总参数量35B，每次推理实际激活参数量约3B72% similarUnverifiedQwen Coder adopts a Mixture of Experts (MoE) architecture with 480 billion total parameters, activating only 35 billion parameters during inference.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/869599API
curl https://kongchang.com/api/v1/knowledge/claims/869599MCP
get_claim(id=869599)