Verified65% confidenceFactExact time
Ornith 1.5 35B-A3B uses a MoE architecture with a total parameter count of approximately 35B, activating only approximately 3B parameters per inference.
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
8/30/2026
First Seen
Valid until: 11/28/2026
Sources
Related Entities
Related Claims
Unverified千问3.6的35B MOE模型每次只激活其中3B的参数80% similarUnverifiedOrnith 35B surpassed Qwen 3.5 and the newer Qwen 3.6 in evaluations and was described by its author as currently the strongest 35B MoE model.78% similarVerifiedHy3 adopts a Mixture of Experts (MoE) architecture with a total parameter count of 295 billion (295B), activating only 21 billion (21B) parameters per inference.74% 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3B73% similarVerified35B-A3B is a MoE architecture naming convention, where 35B refers to a total parameter count of approximately 35 billion, and the A in A3B stands for activated parameters of approximately 3 billion.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/823989API
curl https://kongchang.com/api/v1/knowledge/claims/823989MCP
get_claim(id=823989)