List your company

LLM Inference on MBPP sanitized

2.44Throughput (tokens/s)TIDE
0.8281.24651.6652.0835May 19, 2026

Evaluation results

MethodLinks
TIDEModel=LLaDA2.0-mini, Gen Length=1024, GPU Expert Budget=128, GPU Memory Constraint=18 GB, Block Length=32, Confidence Threshold=0.952026.052.44
TIDEModel=LLaDA2.0-mini, Gen Length=256, GPU Expert Budget=128, GPU Memory Constraint=18 GB, Block Length=32, Confidence Threshold=0.952026.052.36
TIDEModel=LLaDA2.0-mini, Gen Length=256, GPU Expert Budget=64, GPU Memory Constraint=10 GB, Block Length=32, Confidence Threshold=0.952026.052.11
Mixtral-OffloadModel=LLaDA2.0-mini, Gen Length=1024, GPU Expert Budget=128, GPU Memory Constraint=18 GB, Block Length=32, Confidence Threshold=0.952026.051.91
TIDEModel=LLaDA2.0-mini, Gen Length=1024, GPU Expert Budget=64, GPU Memory Constraint=10 GB, Block Length=32, Confidence Threshold=0.952026.051.89
FiddlerModel=LLaDA2.0-mini, Gen Length=256, GPU Expert Budget=64, GPU Memory Constraint=10 GB, Block Length=32, Confidence Threshold=0.952026.051.81
FiddlerModel=LLaDA2.0-mini, Gen Length=1024, GPU Expert Budget=128, GPU Memory Constraint=18 GB, Block Length=32, Confidence Threshold=0.952026.051.8
FiddlerModel=LLaDA2.0-mini, Gen Length=1024, GPU Expert Budget=64, GPU Memory Constraint=10 GB, Block Length=32, Confidence Threshold=0.952026.051.79
Mixtral-OffloadModel=LLaDA2.0-mini, Gen Length=256, GPU Expert Budget=128, GPU Memory Constraint=18 GB, Block Length=32, Confidence Threshold=0.952026.051.76
FiddlerModel=LLaDA2.0-mini, Gen Length=256, GPU Expert Budget=128, GPU Memory Constraint=18 GB, Block Length=32, Confidence Threshold=0.952026.051.74
TIDEModel=LLaDA2.0-flash, Gen Length=256, GPU Expert Budget=64, GPU Memory Constraint=55 GB, Block Length=32, Confidence Threshold=0.952026.051.73
Mixtral-OffloadModel=LLaDA2.0-mini, Gen Length=256, GPU Expert Budget=64, GPU Memory Constraint=10 GB, Block Length=32, Confidence Threshold=0.952026.051.69
Mixtral-OffloadModel=LLaDA2.0-mini, Gen Length=1024, GPU Expert Budget=64, GPU Memory Constraint=10 GB, Block Length=32, Confidence Threshold=0.952026.051.45
TIDEModel=LLaDA2.0-flash, Gen Length=1024, GPU Expert Budget=64, GPU Memory Constraint=55 GB, Block Length=32, Confidence Threshold=0.952026.051.45
Mixtral-OffloadModel=LLaDA2.0-flash, Gen Length=256, GPU Expert Budget=64, GPU Memory Constraint=55 GB, Block Length=32, Confidence Threshold=0.952026.051.35
TIDEModel=LLaDA2.0-flash, Gen Length=256, GPU Expert Budget=32, GPU Memory Constraint=30 GB, Block Length=32, Confidence Threshold=0.952026.051.25
TIDEModel=LLaDA2.0-flash, Gen Length=1024, GPU Expert Budget=32, GPU Memory Constraint=30 GB, Block Length=32, Confidence Threshold=0.952026.051.24
Mixtral-OffloadModel=LLaDA2.0-flash, Gen Length=1024, GPU Expert Budget=64, GPU Memory Constraint=55 GB, Block Length=32, Confidence Threshold=0.952026.051.16
FiddlerModel=LLaDA2.0-flash, Gen Length=256, GPU Expert Budget=64, GPU Memory Constraint=55 GB, Block Length=32, Confidence Threshold=0.952026.051.14
FiddlerModel=LLaDA2.0-flash, Gen Length=1024, GPU Expert Budget=64, GPU Memory Constraint=55 GB, Block Length=32, Confidence Threshold=0.952026.051.05
Mixtral-OffloadModel=LLaDA2.0-flash, Gen Length=256, GPU Expert Budget=32, GPU Memory Constraint=30 GB, Block Length=32, Confidence Threshold=0.952026.051.01
Mixtral-OffloadModel=LLaDA2.0-flash, Gen Length=1024, GPU Expert Budget=32, GPU Memory Constraint=30 GB, Block Length=32, Confidence Threshold=0.952026.051.01
FiddlerModel=LLaDA2.0-flash, Gen Length=256, GPU Expert Budget=32, GPU Memory Constraint=30 GB, Block Length=32, Confidence Threshold=0.952026.050.95
FiddlerModel=LLaDA2.0-flash, Gen Length=1024, GPU Expert Budget=32, GPU Memory Constraint=30 GB, Block Length=32, Confidence Threshold=0.952026.050.89