Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Routing Resource Efficiency on LLM Routing Systems
Loading...
0
GPU Memory Usage (GB)
RouteLLM (MF)
-0.64
3.68
8
12.32
Mar 13, 2026
GPU Memory Usage (GB)
Dedicated GPU Allocation
Updated 1mo ago
Evaluation Results
Method
Method
Links
GPU Memory Usage (GB)
Dedicated GPU Allocation
RouteLLM (MF)
Model=Mat. factorization
2026.03
0
-
RouteLLM (BERT)
Model=0.3B classifier
2026.03
0.6
-
vLLM Semantic Router
Model=3× mmBERT-32K
2026.03
0.8
-
NVIDIA Blueprint
Model=BERT/CLIP + Triton
2026.03
1
-
RouteLLM (Causal)
Model=8B LLM
2026.03
16
-
R2-Router
Model=Reasoning LLM
2026.03
16
-
Feedback
Search any
task
Search any
task