Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Inference Memory Analysis on NVIDIA H100 NVL (seq_len=1024)
Loading...
744
Model Weights Size
Ternary Mamba
560.88
1,796.94
3,033
4,269.06
Jun 16, 2026
Model Weights Size
Peak Inference Memory (bs=1)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Model Weights Size
Peak Inference Memory (bs=1)
Ternary Mamba
Configuration=Ternary...
2026.06
744
1,100
FP16
Configuration=FP16
2026.06
2,599
2,932
Ternary Mamba
Configuration=Ternary...
2026.06
5,322
6,932
Feedback
Search any
task
Search any
task