For model inference, compare energy use as joules per generated token. Measurements with CodeCarbon show lower per-token energy for pruned models, but shared hardware and workload variability make the results comparative baselines, not absolute metrics. section 5.2.6
Table 5.3 Energy efficiency comparison
|
Model
|
Energy
|
Joules / Token
|
Efficiency
|
Tokens Generated
|
|
Base
|
1908.42
|
1.322
|
|
1444
|
|
Wiki model
|
2544.24
|
1.236
|
6.5%
|
2059
|
|
SMS model
|
2473.31
|
1.239
|
6.3%
|
1997
|
Compare energy per token for the base and pruned models. section 5.2.6






