Unverified50% confidenceFactExact time
The research team built MAEM on the basis of Qwen3.6-27B.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/6/2026
First Seen
Valid until: 2/4/2027
Sources
Related Entities
Related Claims
UnverifiedThe Qwen series of models is developed by Alibaba's Tongyi Lab, with 4B and 27B representing the parameter scales.79% similarUnverifiedThe study used three models, Qwen2.5-1.5B, Qwen2.5-3B and Llama-3.2-3B, for experiments.76% similarUnverifiedSimon Willison used the LLM command-line tool together with LM Studio to run Qwen 3.8 27B (17GB, Q4_K_M quantization) for reproduction experiments.73% 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% similarUnverifiedThe user's previous main model was Qwen 3.8 27B, using Q6 quantization and the kv8 configuration.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1142257API
curl https://kongchang.com/api/v1/knowledge/claims/1142257MCP
get_claim(id=1142257)