Expired50% confidenceFactExact time
With unstructured sparsity, even when theoretical computation is reduced by more than 90%, actual execution time may decrease by only 10–20% or even less.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
Related Claims
Unverified少样本方式在格式化输出、分类任务和规则遵循方面的幻觉率可降低40%-70%74% similarUnverified效率型模型以远低于旗舰模型的推理成本（通常低5-10倍）提供接近旗舰模型80-90%的能力表现74% similarUnverifiedAnthropic's research shows that even mild alignment training can cause a 2–8 percentage point decline in model performance on certain reasoning-intensive tasks.72% similarUnverified轻量版模型单次推理的算力消耗往往只有旗舰版本的十分之一甚至更低72% similarUnverifiedUnsloth can reduce memory usage by approximately 70% in some scenarios, and claims no loss of precision.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/42810API
curl https://kongchang.com/api/v1/knowledge/claims/42810MCP
get_claim(id=42810)