Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
Qwen (Alibaba)

Qwen3-VL-30B-A3B-Instruct30B

Benchmark profile and published results.

MoE30B
Position in the field

Best values compared

Best metrics of this model against the minimum, average and maximum of all published systems.

Generation1.655,9 tok/s
Min 0,0Ø 248,3Max 2.491,2
Ueber dem Durchschnitt · 3969 Systeme im Feld
Prefill36.884 tok/s
Min 4Ø 4.741Max 55.260
Ueber dem Durchschnitt · 3969 Systeme im Feld
Time to First Token202 ms
Min 20Ø 33.962Max 535.235
Ueber dem Durchschnitt · 3967 Systeme im Feld
Performance profile

Throughput by hardware & engine

Each bubble is a GPU, CPU or engine – position shows prompt processing (X) and output speed (Y), bubble size the number of runs.

GPUby graphics card

2.1351.6011.0675340,006.96613.93220.898Prefill (tok/s)Generation (tok/s)NVIDIA GeForce RTX 5090 - 1.655,9 tok/s Generation, 9.318 tok/s Prefill, TTFT 3.329 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 1.639,0 tok/s Generation, 17.025 tok/s Prefill, TTFT 1.966 ms (6 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 1.505,0 tok/s Generation, 12.905 tok/s Prefill, TTFT 3.350 ms (9 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 3090 Ti - 903,5 tok/s Generation, 5.934 tok/s Prefill, TTFT 5.817 ms (3 Laufe)NVIDIA GeForce RTX 30...NVIDIA RTX A6000 - 763,5 tok/s Generation, 14.375 tok/s Prefill, TTFT 1.665 ms (36 Laufe)NVIDIA RTX A6000AMD Radeon PRO W7900 Dual Slot - 245,1 tok/s Generation, 4.091 tok/s Prefill, TTFT 3.139 ms (6 Laufe)AMD Radeon PRO W7900 ...AMD Radeon PRO W7800 48GB - 233,0 tok/s Generation, 3.940 tok/s Prefill, TTFT 2.809 ms (4 Laufe)AMD Radeon PRO W7800 ...NVIDIA GeForce RTX 5070 Ti - 154,0 tok/s Generation, 1.182 tok/s Prefill, TTFT 22.532 ms (6 Laufe)NVIDIA GeForce RTX 50...AMD Radeon AI PRO R9700 - 89,8 tok/s Generation, 3.530 tok/s Prefill, TTFT 44.809 ms (20 Laufe)AMD Radeon AI PRO R97...
NVIDIA GeForce RTX 5090 1.655,9 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.639,0 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.505,0 tok/sNVIDIA GeForce RTX 3090 Ti 903,5 tok/sNVIDIA RTX A6000 763,5 tok/sAMD Radeon PRO W7900 Dual Slot 245,1 tok/sAMD Radeon PRO W7800 48GB 233,0 tok/sNVIDIA GeForce RTX 5070 Ti 154,0 tok/sAMD Radeon AI PRO R9700 89,8 tok/s

CPUby processor

2.1041.5781.0525260,006.85913.71820.578Prefill (tok/s)Generation (tok/s)AMD Ryzen 7 5800X3D 8-Core Processor - 1.655,9 tok/s Generation, 9.318 tok/s Prefill, TTFT 3.329 ms (3 Laufe)AMD Ryzen 7 5800X3D 8...AMD Ryzen 9 9950X 16-Core Processor - 1.639,0 tok/s Generation, 17.025 tok/s Prefill, TTFT 1.966 ms (6 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 1.505,0 tok/s Generation, 12.905 tok/s Prefill, TTFT 3.350 ms (9 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 903,5 tok/s Generation, 5.934 tok/s Prefill, TTFT 5.817 ms (3 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 763,5 tok/s Generation, 10.502 tok/s Prefill, TTFT 17.073 ms (56 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 245,1 tok/s Generation, 2.962 tok/s Prefill, TTFT 10.329 ms (16 Laufe)AMD Ryzen Threadrippe...
AMD Ryzen 7 5800X3D 8-Core Processor 1.655,9 tok/sAMD Ryzen 9 9950X 16-Core Processor 1.639,0 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.505,0 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 903,5 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 763,5 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 245,1 tok/s

ENGby engine

2.1351.6011.0675340,03.1657.91112.65717.403Prefill (tok/s)Generation (tok/s)llama.cpp - 1.655,9 tok/s Generation, 7.252 tok/s Prefill, TTFT 20.449 ms (55 Laufe)llama.cppvLLM - 1.028,5 tok/s Generation, 14.863 tok/s Prefill, TTFT 2.006 ms (31 Laufe)vLLMunbekannt - 89,8 tok/s Generation, 5.705 tok/s Prefill, TTFT 549 ms (7 Laufe)unbekannt
llama.cpp 1.655,9 tok/svLLM 1.028,5 tok/sunbekannt 89,8 tok/s
Throughput & latency

Performance benchmark

Metric:
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.655,92 tok/s TG
Prefill 10.520 · TTFT 7.269 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
2Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.639,00 tok/s TG
Prefill 13.790 · TTFT 6.893 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawQ4_K_M
3Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.505,03 tok/s TG
Prefill 19.292 · TTFT 6.959 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
4Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.498,91 tok/s TG
Prefill 15.825 · TTFT 7.173 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
5Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.420,15 tok/s TG
Prefill 10.691 · TTFT 8.165 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
6Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.028,53 tok/s TG
Prefill 36.884 · TTFT 916 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
7Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
920,12 tok/s TG
Prefill 11.397 · TTFT 2.315 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
8Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
905,02 tok/s TG
Prefill 13.235 · TTFT 2.202 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawQ4_K_M
9Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
903,53 tok/s TG
Prefill 7.168 · TTFT 12.726 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketQ4_K_M
10Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
820,05 tok/s TG
Prefill 18.671 · TTFT 2.077 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
11Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
817,68 tok/s TG
Prefill 16.078 · TTFT 2.185 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
12Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
796,67 tok/s TG
Prefill 9.854 · TTFT 2.683 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
13Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
763,50 tok/s TG
Prefill 35.900 · TTFT 987 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
14Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
697,04 tok/s TG
Prefill 30.227 · TTFT 1.164 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
15Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
666,52 tok/s TG
Prefill 27.804 · TTFT 465 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
16Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
547,72 tok/s TG
Prefill 30.727 · TTFT 1.142 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
17Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
542,88 tok/s TG
Prefill 6.558 · TTFT 4.129 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketQ4_K_M
18Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
540,38 tok/s TG
Prefill 12.853 · TTFT 6.483 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
19Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
536,31 tok/s TG
Prefill 26.577 · TTFT 575 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
20Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
536,28 tok/s TG
Prefill 13.681 · TTFT 6.638 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
21Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
516,37 tok/s TG
Prefill 27.317 · TTFT 1.298 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
22Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
469,89 tok/s TG
Prefill 23.294 · TTFT 668 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
23Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
440,04 tok/s TG
Prefill 22.431 · TTFT 1.470 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
24Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
419,38 tok/s TG
Prefill 13.462 · TTFT 8.101 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ8_0
25Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
408,85 tok/s TG
Prefill 12.729 · TTFT 8.436 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ8_0
26Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
386,05 tok/s TG
Prefill 23.773 · TTFT 648 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
27Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
357,72 tok/s TG
Prefill 20.957 · TTFT 747 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
28Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
320,17 tok/s TG
Prefill 11.162 · TTFT 2.744 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliQ4_K_M
29Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
315,88 tok/s TG
Prefill 16.870 · TTFT 841 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
30Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
308,78 tok/s TG
Prefill 11.322 · TTFT 1.153 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
31Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
307,36 tok/s TG
Prefill 6.037 · TTFT 403 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
32Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
303,58 tok/s TG
Prefill 8.051 · TTFT 303 ms
1×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawQ4_K_M
33Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
294,00 tok/s TG
Prefill 18.704 · TTFT 1.760 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
34Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
286,67 tok/s TG
Prefill 12.048 · TTFT 1.249 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
35Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
269,08 tok/s TG
Prefill 5.952 · TTFT 409 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
36Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
268,17 tok/s TG
Prefill 8.954 · TTFT 272 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
37Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
262,06 tok/s TG
Prefill 10.829 · TTFT 225 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
38Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
260,49 tok/s TG
Prefill 10.083 · TTFT 2.921 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliQ8_0
39Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
254,28 tok/s TG
Prefill 8.897 · TTFT 1.540 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliQ4_K_M
40Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
245,10 tok/s TG
Prefill 5.881 · TTFT 4.862 ms
10×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
41Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
233,01 tok/s TG
Prefill 6.125 · TTFT 5.956 ms
10×2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMvLLMgodclawAWQ
42Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
228,83 tok/s TG
Prefill 11.012 · TTFT 1.280 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ8_0
43Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
227,91 tok/s TG
Prefill 2.384 · TTFT 1.021 ms
1×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
44Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
220,51 tok/s TG
Prefill 10.053 · TTFT 1.267 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ8_0
45Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
212,90 tok/s TG
Prefill 14.259 · TTFT 999 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
46Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
200,47 tok/s TG
Prefill 5.590 · TTFT 2.527 ms
5×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
47Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
197,73 tok/s TG
Prefill 4.076 · TTFT 598 ms
1×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketQ4_K_M
48Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
189,14 tok/s TG
Prefill 8.935 · TTFT 1.533 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliQ8_0
49Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
186,58 tok/s TG
Prefill 12.092 · TTFT 202 ms
1×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
50Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
167,54 tok/s TG
Prefill 5.771 · TTFT 422 ms
1×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
51Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
166,85 tok/s TG
Prefill 5.777 · TTFT 422 ms
1×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
52Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
163,97 tok/s TG
Prefill 10.115 · TTFT 241 ms
1×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
53Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
163,29 tok/s TG
Prefill 3.551 · TTFT 3.722 ms
5×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ8_0
54Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
161,14 tok/s TG
Prefill 10.675 · TTFT 228 ms
1×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
55Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
157,64 tok/s TG
Prefill 5.526 · TTFT 441 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliQ4_K_M
56Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
153,96 tok/s TG
Prefill 1.395 · TTFT 74.722 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
57Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
152,42 tok/s TG
Prefill 5.042 · TTFT 3.214 ms
5×2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMvLLMgodclawAWQ
58Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
144,77 tok/s TG
Prefill 8.434 · TTFT 289 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
59Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
143,24 tok/s TG
Prefill 9.105 · TTFT 268 ms
1×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
60Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
128,63 tok/s TG
Prefill 5.799 · TTFT 421 ms
1×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ8_0
61Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
128,49 tok/s TG
Prefill 4.330 · TTFT 571 ms
1×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ8_0
62Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
124,50 tok/s TG
Prefill 4.431 · TTFT 5.687 ms
10×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ8_0
63Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
119,67 tok/s TG
Prefill 5.581 · TTFT 437 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliQ8_0
64Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
116,57 tok/s TG
Prefill 1.336 · TTFT 23.791 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
65Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
110,00 tok/s TG
Prefill 7.008 · TTFT 347 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
66Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
98,01 tok/s TG
Prefill 2.897 · TTFT 845 ms
1×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
67Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmark
89,84 tok/s TG
Prefill 4.031 · TTFT 605 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclaw
68Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmark
86,76 tok/s TG
Prefill 4.914 · TTFT 497 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclaw
69Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmark
86,67 tok/s TG
Prefill 2.692 · TTFT 903 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclaw
70Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
80,66 tok/s TG
Prefill 2.359 · TTFT 978 ms
1×AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ8_0
71Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
69,19 tok/s TG
Prefill 7.289 · TTFT 412 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
72Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmark
69,19 tok/s TG
Prefill 7.289 · TTFT 412 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawAWQ
73Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
63,07 tok/s TG
Prefill 856 · TTFT 2.843 ms
1×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
74Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
61,44 tok/s TG
Prefill 327 · TTFT 206.127 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
75Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
61,41 tok/s TG
Prefill 327 · TTFT 205.729 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
76Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
61,15 tok/s TG
Prefill 324 · TTFT 207.030 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
77Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
54,72 tok/s TG
Prefill 2.235 · TTFT 1.090 ms
1×2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMvLLMgodclawAWQ
78Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
50,52 tok/s TG
Prefill 290 · TTFT 76.173 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
79Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
50,21 tok/s TG
Prefill 288 · TTFT 76.721 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
80Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
50,02 tok/s TG
Prefill 286 · TTFT 77.154 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
81Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
46,18 tok/s TG
Prefill 5.211 · TTFT 480 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
82Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmark
46,18 tok/s TG
Prefill 5.211 · TTFT 480 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawAWQ
83Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
36,87 tok/s TG
Prefill 7.939 · TTFT 473 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
84Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmark
36,87 tok/s TG
Prefill 7.939 · TTFT 473 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawAWQ
85Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
34,36 tok/s TG
Prefill 7.861 · TTFT 473 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
86Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmark
34,36 tok/s TG
Prefill 7.861 · TTFT 473 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawAWQ
87Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
33,62 tok/s TG
Prefill 2.193 · TTFT 1.194 ms
1×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ8_0
88Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
29,41 tok/s TG
Prefill 1.525 · TTFT 19.257 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclawAWQ
89Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
27,94 tok/s TG
Prefill 178 · TTFT 13.764 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
90Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
27,75 tok/s TG
Prefill 177 · TTFT 13.822 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
91Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
27,29 tok/s TG
Prefill 175 · TTFT 13.974 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
92Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
22,64 tok/s TG
Prefill 1.305 · TTFT 10.957 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclawAWQ
93Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
16,34 tok/s TG
Prefill 672 · TTFT 3.622 ms
1×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclawAWQ
Agent & chat rating

Harness benchmark

Noch keine Harnessbenchmarks fuer dieses Modell.