Unverified50% confidenceFactExact time
In the CED architecture, only 8B parameters are activated on the input side, while 16B parameters are activated on the output side.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAfter adopting the causal encoder-decoder, the activated parameters per token during the prefill phase were reduced from 16B to 8B.68% similarUnverifiednomic-embed-text嵌入模型有137M参数，all-MiniLM-L6-v2有22M参数，BGE-small为24M-109M参数61% similarUnverifiedLFM2.5-8B-A1B总参数量为8B，推理时仅激活1.5B参数60% similarVerifiedFP32每个参数占4字节，FP16/BF16占2字节，INT8量化占1字节，INT4量化占0.5字节60% similarUnverifiedIn speculative decoding, the draft model's parameter count is typically about 1/10 to 1/5 of the target model, and the candidate count k is typically 4-8.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/900391API
curl https://kongchang.com/api/v1/knowledge/claims/900391MCP
get_claim(id=900391)