🏆
Ranglisten
LLM Leaderboard
Reale Messergebnisse aller getesteten Sprachmodelle auf echter, benannter Hardware – bewertet nach roher Geschwindigkeit (Performance in Token pro Sekunde, Prefill und Zeit bis zum ersten Token) und nach praktischer Aufgaben-Qualität in vollständigen Agenten- und Chat-Abläufen (Harness). Wähle unten einen Benchmark-Typ oder filtere nach Modell, Hersteller und Hardware, um genau zu sehen, was jeweils geprüft wird und wie die Ergebnisse zustande kommen.
⚡ Performance (tok/s)🤖 Harness-Qualität👥 Concurrency🖥️ echte Hardware
| # | Modell / Hersteller | Messwerte | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 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 RAM | vLLMgodclawAWQ | Details → | |
| 2 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 850,30 tok/s TG Prefill 14.558 · TTFT 681 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 3 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 847,27 tok/s TG Prefill 14.549 · TTFT 681 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 4 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 845,91 tok/s TG Prefill 14.817 · TTFT 667 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 5 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 839,65 tok/s TG Prefill 14.503 · TTFT 682 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 6 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 773,21 tok/s TG Prefill 17.224 · TTFT 1.181 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 7 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 772,60 tok/s TG Prefill 16.608 · TTFT 1.217 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 8 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 770,10 tok/s TG Prefill 17.225 · TTFT 1.181 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 9 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 769,38 tok/s TG Prefill 17.501 · TTFT 1.163 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 10 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 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 RAM | vLLMgodclawAWQ | Details → | |
| 11 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 475,79 tok/s TG Prefill 6.572 · TTFT 3.089 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 12 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 471,61 tok/s TG Prefill 6.627 · TTFT 3.065 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 13 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 469,71 tok/s TG Prefill 6.608 · TTFT 3.074 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 14 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 468,50 tok/s TG Prefill 6.586 · TTFT 3.084 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 15 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 464,61 tok/s TG Prefill 5.872 · TTFT 1.691 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 16 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,98 tok/s TG Prefill 5.865 · TTFT 1.693 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 17 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 461,82 tok/s TG Prefill 5.854 · TTFT 1.696 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 18 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 458,88 tok/s TG Prefill 5.872 · TTFT 1.692 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 19 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 404,99 tok/s TG Prefill 9.572 · TTFT 208 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 20 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 399,47 tok/s TG Prefill 10.662 · TTFT 185 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 21 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 397,95 tok/s TG Prefill 10.745 · TTFT 184 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 22 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 397,73 tok/s TG Prefill 10.586 · TTFT 187 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 23 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,35 tok/s TG Prefill 5.558 · TTFT 356 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 24 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,95 tok/s TG Prefill 5.518 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 25 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,85 tok/s TG Prefill 5.565 · TTFT 356 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 26 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,24 tok/s TG Prefill 5.475 · TTFT 361 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 27 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 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 RAM | vLLMgodclawAWQ | Details → | |
| 28 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 186,92 tok/s TG Prefill 4.641 · TTFT 2.689 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 29 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 167,15 tok/s TG Prefill 6.281 · TTFT 4.625 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 30 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 102,19 tok/s TG Prefill 2.357 · TTFT 12.337 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 31 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 95,43 tok/s TG Prefill 1.761 · TTFT 7.081 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 32 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 91,90 tok/s TG Prefill 1.232 · TTFT 16.476 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 33 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 91,87 tok/s TG Prefill 1.224 · TTFT 16.600 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 34 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 90,10 tok/s TG Prefill 1.233 · TTFT 16.472 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 35 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 89,84 tok/s TG Prefill 1.231 · TTFT 16.475 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 36 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 89,84 tok/s TG Prefill 4.031 · TTFT 605 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 37 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,10 tok/s TG Prefill 1.103 · TTFT 9.009 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 38 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 87,71 tok/s TG Prefill 1.119 · TTFT 8.888 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 39 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 86,76 tok/s TG Prefill 4.914 · TTFT 497 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 40 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 86,67 tok/s TG Prefill 2.692 · TTFT 903 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 41 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 73,81 tok/s TG Prefill 1.108 · TTFT 8.965 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 42 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 71,41 tok/s TG Prefill 1.112 · TTFT 8.937 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 43 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 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 RAM | vLLMgodclawAWQ | Details → | |
| 44 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 68,33 tok/s TG Prefill 1.093 · TTFT 1.983 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 45 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,17 tok/s TG Prefill 1.117 · TTFT 1.771 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 46 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,11 tok/s TG Prefill 1.113 · TTFT 1.777 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 47 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,90 tok/s TG Prefill 1.104 · TTFT 1.792 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 48 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,74 tok/s TG Prefill 1.106 · TTFT 1.790 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 49 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 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 RAM | vLLMgodclawAWQ | Details → | |
| 50 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 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 RAM | vLLMgodclawAWQ | Details → | |
| 51 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 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 RAM | vLLMgodclawAWQ | Details → | |
| 52 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 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 RAM | vLLMgodclawAWQ | Details → | |
| 53 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 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 RAM | vLLMgodclawAWQ | Details → | |
| 54 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 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 RAM | vLLMgodclawAWQ | Details → |