Unverified50% confidenceFactExact time
DeepSeek-V4.1 uses an asymmetric activated-parameter design: only 8B parameters are activated on input and 16B parameters on output, while KV Cache and memory usage are significantly reduced compared with the previous generation.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedDeepSeek-V4.1-Flash activates only 8B parameters during the prompt reading phase and activates 16B parameters during the output generation phase.76% similarUnverifiedDeepSeek v4.1-Flash 1017 is a sparse MoE model with 284B total parameters that activates only 13B parameters per token.72% similarUnverifiedDeepSeek released DeepSeek-V4.1-Flash, a method that significantly compresses the memory required for KV cache.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1061737API
curl https://kongchang.com/api/v1/knowledge/claims/1061737MCP
get_claim(id=1061737)