Unverified50% confidenceFactExact time
The main model of the architecture used by Qwen4 has 125B parameters, activates only 6B per token, uses a MoE architecture, contains 512 experts, and has a native context of 262K.
1
Sources
50%
Confidence
Long-term
Relevance
10/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedQwen3.8-Flash-Next has a 48-layer structure with 512 experts per layer and 180B-class parameters (125B main body + 51B N-gram table + 4B MTP).76% similarUnverifiedThe Qwen series of models is developed by Alibaba's Tongyi Lab, with 4B and 27B representing the parameter scales.74% similarUnverifiedLFM2.5-24B-A2B has 24 billion total parameters and uses an MoE architecture with 64 experts per block, Top-4 dynamic routing, and only 2.45 billion parameters activated per token.73% 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% similarUnverifiedQwen3.5-122B-A10B is a MoE architecture model with approximately 122B total parameters and approximately 10B activated parameters, activating only about 10 billion parameters per inference.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1112067API
curl https://kongchang.com/api/v1/knowledge/claims/1112067MCP
get_claim(id=1112067)