SST trades lower bulk-prefill active-body count for higher decode active-body count relative to 47B classic. Under the paper's common analytical proxy, SST becomes cheaper than 47B once prefill weight exceeds 65.5% and cheaper than 63B above 13.4%; at a 75:25 prefill:decode mix it is estimated 6.7% below 47B and 31.6% below 63B.

SST trades lower bulk-prefill active-body count for higher decode active-body count relative to 47B classic. Under the paper's common analytical proxy, SST becomes cheaper than 47B once prefill weight exceeds 65.5% and cheaper than 63B above 13.4%; at a 75:25 prefill:decode mix it is estimated 6.7% below 47B and 31.6% below 63B. · CiteArk

测量结果

已评估 0/18 项

获得支持 0有争议或冲突 0尚未评估 18

保留同一结论下的完整结果组。已有评估排在前面；单项判断不替代整组结论。展开行查看条件、来源与历次证据。

每行是一项测量，分别显示论文报告、最近可用实测和累计证据状态。
指标与条件	论文报告	最近可用实测	证据判断
model: 67B SST · component: Prefiller only	1.12 billion parameters per token	—	尚未评估
model: 67B SST · components: Prefiller + Decoder	2.155 billion parameters per token	—	尚未评估
model: 47B classic	1.477 billion parameters per token	—	尚未评估
model: 63B classic	2.016 billion parameters per token	—	尚未评估
model: 67B SST · decode_weight_percent: 25 · prefill_weight_percent: 75	0.933 fraction of 47B classic	—	尚未评估
model: 47B classic · decode_weight_percent: 25 · prefill_weight_percent: 75	1 fraction of 47B classic	—	尚未评估
model: 63B classic · decode_weight_percent: 25 · prefill_weight_percent: 75	1.365 fraction of 47B classic	—	尚未评估
model: 63B classic · comparison: 47B classic · prefill_decode_mix: 75:25	36.5%	—	尚未评估
model: 67B SST · comparison: 47B classic · prefill_decode_mix: 75:25	6.7%	—	尚未评估
model: 67B SST · comparison: 63B classic · prefill_decode_mix: 75:25	31.6%	—	尚未评估
models: 67B SST and 47B classic · decode_weight_percent: 34.5	65.5%	—	尚未评估
models: 67B SST and 63B classic · decode_weight_percent: 86.6	13.4%	—	尚未评估

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果