Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Inference Throughput on Qwen3 Models (test)

120.62Throughput (k tokens/sec)

AWQ

6.365636.027865.6995.3522Mar 11, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.03
120.62
2026.03
116.82
2026.03
115.2
2026.03
113.84
2026.03
112.61
2026.03
108
2026.03
104.11
2026.03
103.45
2026.03
101
2026.03
92.23
2026.03
90.42
2026.03
80.45
2026.03
80.19
2026.03
77.88
2026.03
77.04
2026.03
74.72
2026.03
73.47
2026.03
72.55
2026.03
72.45
2026.03
72.34
2026.03
67.4
2026.03
66.62
2026.03
62.94
2026.03
58.65
2026.03
58.44
2026.03
53.17
2026.03
51.32
2026.03
50.45
2026.03
46.78
2026.03
10.76