Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

End-to-end decode throughput on Context Length 32K

183Decode Throughput (tok/s)

Llama-3.1-8B

89.712113.931138.15162.369May 13, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2026.05
183
2026.05
172.5
2026.05
153.9
2026.05
110
2026.05
104.9
2026.05
93.3