Back to models
publish

Qwen3-VL

Qwen3-VL

Avg speed
57.81t/s
First token
12.92s
Total tests
75
Providers
6
Variants
7

Variants

Showing 1-7 of 7 providers

VariantSpeedLatencyTests
DashScope
147.58 t/s
1.00s
5
SiliconFlow
142.73 t/s
0.64s
5

Recent test records

20 records
TimeModelSpeedLatency
Feb 25, 07:51 AMQwen/Qwen3-VL-32B-Thinking
42.79 t/s
14.78s
Feb 25, 07:51 AMQwen/Qwen3-VL-32B-Thinking
81.95 t/s
24.49s
Feb 25, 07:51 AMQwen/Qwen3-VL-32B-Thinking
85.94 t/s
0.56s
5
Fireworks AIaccounts/fireworks/models/qwen3-vl-235b-a22b-thinking
51.54 t/s
1.25s
5
OpenRouterqwen/qwen3-vl-32b-instruct
44.94 t/s
0.76s
5
DashScopeqwen3-vl-235b-a22b-instruct
41.54 t/s
3.23s
5
Qwen/Qwen3-VL-32B-Thinking
39.21 t/s
20.71s
45
66.84 t/s
50.11s
Feb 25, 07:51 AMQwen/Qwen3-VL-32B-Thinking
67.02 t/s
5.31s
Feb 25, 07:51 AMQwen/Qwen3-VL-32B-Thinking
46.21 t/s
16.85s
Jan 19, 12:03 AMqwen3-vl-flash
97.60 t/s
0.66s
Jan 19, 12:03 AMqwen3-vl-flash
64.67 t/s
0.60s
Jan 19, 12:03 AMqwen3-vl-flash
76.74 t/s
0.49s
Jan 19, 12:03 AMqwen3-vl-flash
96.80 t/s
0.54s
Jan 19, 12:03 AMqwen3-vl-flash
93.87 t/s
0.52s
Jan 15, 01:36 PMQwen/Qwen3-VL-32B-Thinking
30.68 t/s
15.67s
Jan 15, 01:36 PMQwen/Qwen3-VL-32B-Thinking
51.81 t/s
7.51s
Jan 15, 01:36 PMQwen/Qwen3-VL-32B-Thinking
43.77 t/s
16.11s
Jan 15, 01:36 PMQwen/Qwen3-VL-32B-Thinking
58.24 t/s
7.63s
Jan 15, 01:36 PMQwen/Qwen3-VL-32B-Thinking
37.82 t/s
24.50s
Jan 13, 01:15 AMaccounts/fireworks/models/qwen3-vl-235b-a22b-thinking
57.56 t/s
0.80s
Jan 13, 01:15 AMaccounts/fireworks/models/qwen3-vl-235b-a22b-thinking
50.39 t/s
0.44s
Jan 13, 01:15 AMaccounts/fireworks/models/qwen3-vl-235b-a22b-thinking
49.90 t/s
3.94s
Jan 13, 01:15 AMaccounts/fireworks/models/qwen3-vl-235b-a22b-thinking
50.66 t/s
0.64s
Jan 13, 01:15 AMaccounts/fireworks/models/qwen3-vl-235b-a22b-thinking
49.21 t/s
0.44s
qwen3-vl-flash
Qwen/Qwen3-VL-8B-Instruct
qwen3-vl-flash