Back to models
publish

Qwen3

Qwen3

Avg speed
28.87t/s
First token
23.56s
Total tests
7,653
Providers
41
Variants
100

Variants

Showing 1-100 of 100 providers

VariantSpeedLatencyTests
RinkoAI
1214.07 t/s
0.91s
5
RinkoAI
552.48 t/s
0.89s
5
RinkoAI

Recent test records

20 records
TimeModelSpeedLatency
Feb 27, 09:02 PMqwen/qwen3.5-397b-a17b
29.59 t/s
1.12s
Feb 27, 09:02 PMqwen/qwen3.5-397b-a17b
40.16 t/s
4.76s
Feb 27, 09:02 PMqwen/qwen3.5-397b-a17b
272.18 t/s
1.71s
25
qwen3-1.7b
171.33 t/s
3.66s
10
DashScopeqwen3-next-80b-a3b-instruct
158.86 t/s
2.22s
10
DashScopeqwen3-1.7b
155.43 t/s
4.85s
10
DashScopeqwen3-vl-flash
147.58 t/s
1.00s
5
1984vllm.Qwen/Qwen3-Coder-30B-A3B-Instruct
145.28 t/s
1.06s
5
Anannasqwen/qwen3-next-80b-a3b-instruct
144.83 t/s
0.81s
25
SiliconFlowQwen/Qwen3-VL-8B-Instruct
142.73 t/s
0.64s
5
Qwen/Qwen3-Next-80B-A3B-Instruct
141.53 t/s
1.06s
35
qwen3-1.7b:free
133.77 t/s
5.08s
5
Qwen/Qwen3-235B-A22B
116.62 t/s
21.27s
30
TokenPonyqwen3-8b
111.05 t/s
7.64s
15
qwen/qwen3-32b
109.71 t/s
10.44s
20
OpenRouterqwen/qwen3-30b-a3b
105.64 t/s
13.53s
60
Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8
89.43 t/s
0.36s
5
qwen3-vl-flash
85.94 t/s
0.56s
5
OpenRouterqwen/qwen3-30b-a3b:free
83.19 t/s
22.71s
5
Hornsununsloth/qwen3:30b-a3b-q8_0
82.71 t/s
2.21s
5
qwen/qwen3-14b
81.49 t/s
18.89s
5
qwen3-8b
78.65 t/s
10.01s
5
Fireworks AIaccounts/fireworks/models/qwen3-235b-a22b-instruct-2507
78.64 t/s
0.62s
5
New APIQwen/Qwen3-32B-FP8
75.12 t/s
1.01s
5
ModelScopeQwen/Qwen3-30B-A3B
67.09 t/s
18.06s
45
Qwen/Qwen3-235B-A22B-FP8
66.11 t/s
14.31s
5
qwen3-235b-a22b-instruct-2507
65.96 t/s
1.19s
5
qwen3-omni-flash-2025-12-01
65.20 t/s
5.13s
5
qwen3-30b-a3b
64.07 t/s
8.79s
25
Hornsunqwen3:30b-a3b-q8_0
63.96 t/s
0.58s
10
共绩算力qwen3:30b-a3b
63.68 t/s
1.76s
80
Hugging FaceQwen/Qwen3-Coder-480B-A35B-Instruct:novita
63.59 t/s
1.06s
5
YuegleQwen/Qwen3-235B-A22B-Instruct-2507-FP8
63.17 t/s
0.70s
5
RinkoAIQwen/Qwen3-14B
62.61 t/s
8.14s
15
Hornsununsloth/qwen3:14b-q8_0
61.79 t/s
1.51s
5
New APIqwen3
59.87 t/s
5.39s
5
YUNWU APIqwen3-coder-480b-a35b-instruct
58.38 t/s
1.43s
10
qwen3-coder-plus
54.19 t/s
1.08s
10
SiliconFlowdeepseek-ai/DeepSeek-R1-0528-Qwen3-8B
53.62 t/s
28.33s
30
DashScopeqwen3-235b-a22b-thinking-2507
53.49 t/s
13.88s
20
Fireworks AIaccounts/fireworks/models/qwen3-vl-235b-a22b-thinking
51.54 t/s
1.25s
5
并行科技Qwen3-235B-A22B-Thinking-2507
48.00 t/s
13.71s
5
OpenRouterqwen/qwen3-vl-32b-instruct
44.94 t/s
0.76s
5
DashScopeqwen3-max-preview
44.58 t/s
0.77s
5
qwen3:30b
44.38 t/s
0.67s
40
HaruiQwen3-235B-A22B-Instruct-2507
43.21 t/s
1.05s
5
DashScopeqwen3-235b-a22b-instruct-2507
43.21 t/s
0.95s
15
XJY APIqwen/qwen3.5-397b-a17b
43.19 t/s
1.56s
5
DashScopeqwen3-vl-235b-a22b-instruct
41.54 t/s
3.23s
5
MineQwen3-235B-A22B
40.69 t/s
7.58s
10
AIHubMixalicloud-qwen3-max-2026-01-23
40.59 t/s
1.26s
5
qwen/qwen3-coder
40.47 t/s
8.05s
33
Qwen/Qwen3-VL-32B-Thinking
39.21 t/s
20.71s
45
qwen3-235b-a22b
39.18 t/s
15.96s
35
SiliconFlowQwen/Qwen3-Coder-30B-A3B-Instruct
38.23 t/s
0.78s
5
ModelScopeQwen/Qwen3-8B
38.15 t/s
35.75s
65
共绩算力qwen3:32b
36.77 t/s
3.71s
40
Hugging FaceQwen/Qwen3-235B-A22B:novita
34.12 t/s
1.12s
5
integrate.api.nvidia.comqwen/qwen3-235b-a22b
28.79 t/s
16.83s
15
qwen/qwen3-8b
28.77 t/s
0.95s
50
并行科技Qwen3-32B
27.00 t/s
39.79s
15
DashScopeqwen3-max-2025-09-23
26.41 t/s
1.25s
10
心流qwen3-235b-a22b-instruct
24.36 t/s
0.39s
10
integrate.api.nvidia.comqwen/qwen3.5-397b-a17b
23.36 t/s
0.71s
5
SiliconFlowQwen/Qwen3-235B-A22B-Instruct-2507
20.96 t/s
1.49s
15
Groqfree:Qwen3-30B-A3B
20.90 t/s
25.83s
6570
free:Qwen3-30B-A3B
19.62 t/s
7.50s
30
ngrokqwen/qwen3-coder-30b
18.83 t/s
2.36s
10
SiliconFlowQwen3-235B-A22B
-
-s
0
DashScopeqwen3-32b
-
-s
0
心流qwen3-32b
-
-s
0
Hornsunqwen3:30b-a3b
-
-s
0
SiliconFlowQwen/Qwen3-14B
-
-s
0
DashScopeqwen3-coder-plus
-
-s
0
OpenRouterqwen/qwen3-235b-a22b:free
-
-s
0
New APIQwen/Qwen3-30B-A3B
-
-s
0
qwen/qwen3-next-80b-a3b-instruct
-
-s
0
SiliconFlowQwen/Qwen3-32B
-
-s
0
ModelScopeQwen/Qwen3-235B-A22B-Instruct-2507
-
-s
0
integrate.api.nvidia.comqwen/qwen3-next-80b-a3b-instruct
-
-s
0
TokenPonyqwen3-next-80b-a3b-instruct
-
-s
0
DashScopeqwen3-8b
-
-s
0
ModelScopeQwen/Qwen3-Next-80B-A3B-Instruct
-
-s
0
RinkoAIQwen/Qwen3-30B-A3B
-
-s
0
共绩算力qwen3:32b
-
-s
0
SiliconFlowQwen/Qwen3-30B-A3B-Instruct-2507
-
-s
0
DMXAPIqwen3-32b
-
-s
0
DashScopeqwen3-0.6b
-
-s
0
SiliconFlowQwen/Qwen3-235B-A22B
-
-s
0
qwen3-coder-flash
-
-s
0
SiliconFlowQwen/Qwen3-8B
-
-s
0
DashScopeqwen3-235b-a22b
-
-s
0
DashScopeqwen3-30b-a3b
-
-s
0
ModelScopeQwen/Qwen3-Coder-30B-A3B-Instruct
-
-s
0
SiliconFlowQwen/Qwen3-Next-80B-A3B-Instruct
-
-s
0
OpenRouterQwen: Qwen3 235B A22B (free)
-
-s
0
qwen/qwen3-30b-a3b
-
-s
0
qwen/qwen3-235b-a22b
-
-s
0
DMXAPIqwen3-235b-a22b
-
-s
0
SiliconFlowQwen/Qwen3-30B-A3B
-
-s
0
21.22 t/s
0.72s
Feb 27, 09:02 PMqwen/qwen3.5-397b-a17b
62.82 t/s
0.60s
Feb 27, 09:02 PMqwen/qwen3.5-397b-a17b
62.17 t/s
0.59s
Feb 26, 01:17 PMqwen/qwen3.5-397b-a17b
31.34 t/s
0.48s
Feb 26, 01:17 PMqwen/qwen3.5-397b-a17b
22.11 t/s
0.52s
Feb 26, 01:17 PMqwen/qwen3.5-397b-a17b
32.72 t/s
0.81s
Feb 26, 01:17 PMqwen/qwen3.5-397b-a17b
10.00 t/s
1.36s
Feb 26, 01:17 PMqwen/qwen3.5-397b-a17b
20.64 t/s
0.35s
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
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
Feb 16, 03:20 AMqwen3-1.7b:free
134.16 t/s
4.84s
Feb 16, 03:20 AMqwen3-1.7b:free
153.81 t/s
4.20s
Feb 16, 03:20 AMqwen3-1.7b:free
140.39 t/s
7.20s
Feb 16, 03:20 AMqwen3-1.7b:free
81.87 t/s
4.83s
Feb 16, 03:20 AMqwen3-1.7b:free
158.63 t/s
4.32s
Qwen/Qwen3-32B
Qwen/Qwen3-Coder-480B
Qwen/Qwen3-235B