Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Inference on Qwen3-8B workload (c=512) on RTX PRO 6000
Loading...
80.3
SLO Attainment (%)
EB+
-3.212
18.469
40.15
61.831
May 30, 2026
SLO Attainment (%)
Updated 1d ago
Evaluation Results
Method
Method
Links
SLO Attainment (%)
EB+
TTFT target=<10 s, TPO...
2026.05
80.3
EB(k*)
TTFT target=<10 s, TPO...
2026.05
77.3
EB+
TTFT target=<5 s, TPOT...
2026.05
48.4
EB(k*)
TTFT target=<5 s, TPOT...
2026.05
6.2
v1
TTFT target=<10 s, TPO...
2026.05
5.8
v1
TTFT target=<5 s, TPOT...
2026.05
5
v1
TTFT target=<2 s, TPOT...
2026.05
4.9
EB+
TTFT target=<10 s, TPO...
2026.05
1.3
EB+
TTFT target=<2 s, TPOT...
2026.05
1.2
EB+
TTFT target=<5 s, TPOT...
2026.05
1.1
v1
TTFT target=<2 s, TPOT...
2026.05
0.6
v1
TTFT target=<5 s, TPOT...
2026.05
0.6
v1
TTFT target=<10 s, TPO...
2026.05
0.6
EB(k*)
TTFT target=<10 s, TPO...
2026.05
0.5
EB(k*)
TTFT target=<2 s, TPOT...
2026.05
0
EB+
TTFT target=<2 s, TPOT...
2026.05
0
EB(k*)
TTFT target=<5 s, TPOT...
2026.05
0
EB(k*)
TTFT target=<2 s, TPOT...
2026.05
0
Feedback
Search any
task
Search any
task
