Qwen3
158.86 t/s |
2.22s |
| 10 |
155.43 t/s | 4.85s | 10 |
147.58 t/s | 1.00s | 5 |
145.28 t/s | 1.06s | 5 |
144.83 t/s | 0.81s | 25 |
142.73 t/s | 0.64s | 5 |
| Qwen/Qwen3-Next-80B-A3B-Instruct | 141.53 t/s | 1.06s | 35 |
| Qwen/Qwen3-235B-A22B | 116.62 t/s | 21.27s | 30 |
111.05 t/s | 7.64s | 15 |
| qwen/qwen3-32b | 109.71 t/s | 10.44s | 20 |
105.64 t/s | 13.53s | 60 |
| Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 | 89.43 t/s | 0.36s | 5 |
83.19 t/s | 22.71s | 5 |
82.71 t/s | 2.21s | 5 |
| qwen/qwen3-14b | 81.49 t/s | 18.89s | 5 |
78.64 t/s | 0.62s | 5 |
75.12 t/s | 1.01s | 5 |
73.52 t/s | 6.67s | 5 |
67.09 t/s | 18.06s | 45 |
| Qwen/Qwen3-235B-A22B-FP8 | 66.11 t/s | 14.31s | 5 |
| qwen3-30b-a3b | 64.07 t/s | 8.79s | 25 |
63.96 t/s | 0.58s | 10 |
63.59 t/s | 1.06s | 5 |
63.17 t/s | 0.70s | 5 |
62.61 t/s | 8.14s | 15 |
61.79 t/s | 1.51s | 5 |
59.87 t/s | 5.39s | 5 |
58.38 t/s | 1.43s | 10 |
| qwen3-coder-plus | 54.19 t/s | 1.08s | 10 |
53.62 t/s | 28.33s | 30 |
48.00 t/s | 13.71s | 5 |
44.94 t/s | 0.76s | 5 |
| qwen3:30b | 44.38 t/s | 0.67s | 40 |
43.21 t/s | 1.05s | 5 |
| qwen/qwen3-coder | 42.16 t/s | 3.74s | 25 |
41.54 t/s | 3.23s | 5 |
40.69 t/s | 7.58s | 10 |
39.59 t/s | 38.65s | 60 |
| qwen3-235b-a22b | 39.18 t/s | 15.96s | 35 |
37.24 t/s | 18.95s | 10 |
| Qwen/Qwen3-VL-32B-Thinking | 34.34 t/s | 24.57s | 20 |
34.12 t/s | 1.12s | 5 |
28.79 t/s | 16.83s | 15 |
27.00 t/s | 39.79s | 15 |
24.80 t/s | 1.15s | 5 |
24.49 t/s | 1.14s | 5 |
24.36 t/s | 0.39s | 10 |
23.80 t/s | 1.89s | 10 |
20.88 t/s | 25.90s | 6515 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
| qwen3-coder-flash | - | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
| free:Qwen3-30B-A3B | - | -s | 0 |
| qwen/qwen3-30b-a3b | - | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
| qwen/qwen3-next-80b-a3b-instruct | - | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
- | -s | 0 |
| qwen/qwen3-235b-a22b | - | -s | 0 |
- | -s | 0 |
362.78 t/s |
0.14s |
| Dec 12, 12:40 AM | qwen/qwen3-32b | 288.75 t/s | 0.29s |
| Dec 12, 12:40 AM | qwen/qwen3-32b | 347.02 t/s | 0.14s |
| Dec 11, 06:25 AM | Qwen/Qwen3-VL-32B-Thinking | 24.07 t/s | 31.34s |
| Dec 11, 06:25 AM | Qwen/Qwen3-VL-32B-Thinking | 23.05 t/s | 90.25s |
| Dec 11, 06:25 AM | Qwen/Qwen3-VL-32B-Thinking | 20.13 t/s | 39.93s |
| Dec 11, 06:25 AM | Qwen/Qwen3-VL-32B-Thinking | 20.65 t/s | 18.19s |
| Dec 11, 06:25 AM | Qwen/Qwen3-VL-32B-Thinking | 19.36 t/s | 51.10s |
| Dec 8, 06:30 AM | free:Qwen3-30B-A3B | 22.08 t/s | 50.23s |
| Dec 8, 06:30 AM | free:Qwen3-30B-A3B | 12.86 t/s | 7.47s |
| Dec 8, 06:30 AM | free:Qwen3-30B-A3B | 13.35 t/s | 0.85s |
| Dec 8, 06:30 AM | free:Qwen3-30B-A3B | 30.36 t/s | 0.64s |
| Dec 8, 06:30 AM | free:Qwen3-30B-A3B | 15.83 t/s | 0.79s |
| Dec 8, 06:24 AM | free:Qwen3-30B-A3B | 38.75 t/s | 16.75s |
| Dec 8, 06:24 AM | free:Qwen3-30B-A3B | 18.65 t/s | 0.65s |
| Dec 8, 06:24 AM | free:Qwen3-30B-A3B | 8.90 t/s | 19.29s |
| Dec 8, 06:24 AM | free:Qwen3-30B-A3B | 23.71 t/s | 0.56s |
| Dec 8, 06:24 AM | free:Qwen3-30B-A3B | 25.07 t/s | 1.06s |