Verified65% confidenceFactExact time
Qwen3.8-Flash-Next has approximately 6B activated parameters.
3
Sources
65%
Confidence
Long-term
Relevance
9/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAccording to official data, Qwen3.8-Flash-Next surpasses Claude Opus 4.6 Max in both text and multimodal domains with only 6B activated parameters, and its training cost is only one-ninth of Qwen3.7-Plus.76% similarUnverifiedQwen3.8 Flash Next has 125 billion total parameters, with only approximately 6 billion parameters activated per token during inference76% similarUnverifiedQwen3.8-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).74% similarUnverifiedThe activated parameter count of Qwen3.8 Flash is approximately one-third that of GLM.74% similarUnverifiedThe user's previous main model was Qwen 3.8 27B, using Q6 quantization and the kv8 configuration.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/863504API
curl https://kongchang.com/api/v1/knowledge/claims/863504MCP
get_claim(id=863504)