Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Inference Efficiency on HumanEval
Loading...
5,233.11
TTFT (ms)
ReMoE
5,155.0032
5,682.2241
6,209.445
6,736.6659
May 26, 2026
TTFT (ms)
TPOT (ms)
Decode Speed Factor
Updated 7d ago
Evaluation Results
Method
Method
Links
TTFT (ms)
TPOT (ms)
Decode Speed Factor
ReMoE
Hardware=Jetson Orin N...
2026.05
5,233.11
337.61
1.99
Baseline
Hardware=Jetson Orin N...
2026.05
7,185.78
672.68
-
Feedback
Search any
task
Search any
task
