Unverified50% confidenceFactExact time
Qwen4-Max has a parameter scale of 2.4T total parameters, with 71B activated parameters.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/16/2026
First Seen
Valid until: 2/14/2027
Sources
Related Entities
Related Claims
UnverifiedQwen2.5-Max-0902 has a maximum output of 130,000 tokens, with the limit rising to 260,000 tokens in reasoning mode.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.73% similarVerifiedQwen3.5's parameter activation rate is 4.3%, while DeepSeek V3's 671B model has an activation rate of 5.5%.73% similarUnverifiedIn Qwen3.8-2.4T-A95B, 2.4T means the model's total parameter count is about 2.4 trillion, and in A95B, A stands for Activated, with about 95 billion parameters actually activated per forward pass.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1174817API
curl https://kongchang.com/api/v1/knowledge/claims/1174817MCP
get_claim(id=1174817)