⚡
Performance-Benchmark
Wie schnell ist das Modell?
Roher Durchsatz auf echter Hardware – wie viele Token ein Modell pro Sekunde erzeugt, wie schnell es den Prompt verarbeitet und wie kurz die Zeit bis zum ersten Token ausfällt. Je höher, desto besser.
⚡ Generation (tok/s)🔄 Prefill⏱️ TTFT👥 Concurrency
| # | Modell / Hersteller | Messwerte | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 388,05 tok/s TG Prefill 16.198 · TTFT 2.053 ms | 10× | 2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAM | vLLMgodclawINT4 | Details → | |
| 2 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 343,90 tok/s TG Prefill 9.629 · TTFT 1.973 ms | 5× | 2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAM | vLLMgodclawINT4 | Details → | |
| 3 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 201,32 tok/s TG Prefill 2.330 · TTFT 11.380 ms | 10× | 2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 110 GB RAM | llama.cppgodclaw | Details → | |
| 4 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 197,94 tok/s TG Prefill 2.288 · TTFT 11.557 ms | 10× | 2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 5 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 194,68 tok/s TG Prefill 1.934 · TTFT 12.719 ms | 10× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 6 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 190,45 tok/s TG Prefill 1.680 · TTFT 6.722 ms | 5× | 2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 110 GB RAM | llama.cppgodclaw | Details → | |
| 7 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 190,09 tok/s TG Prefill 1.655 · TTFT 6.827 ms | 5× | 2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 8 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 184,78 tok/s TG Prefill 1.567 · TTFT 7.199 ms | 5× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 9 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 99,60 tok/s TG Prefill 4.438 · TTFT 606 ms | 1× | 2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAM | vLLMgodclawINT4 | Details → | |
| 10 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 92,62 tok/s TG Prefill 1.185 · TTFT 24.873 ms | 10× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 11 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 90,29 tok/s TG Prefill 1.380 · TTFT 1.577 ms | 1× | 2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 110 GB RAM | llama.cppgodclaw | Details → | |
| 12 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 89,66 tok/s TG Prefill 1.349 · TTFT 1.612 ms | 1× | 2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 13 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 87,74 tok/s TG Prefill 1.275 · TTFT 1.916 ms | 1× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 14 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 79,19 tok/s TG Prefill 670 · TTFT 33.965 ms | 10× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 126 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 15 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 73,50 tok/s TG Prefill 900 · TTFT 14.075 ms | 5× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 16 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 73,30 tok/s TG Prefill 487 · TTFT 20.813 ms | 5× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 126 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 17 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 71,73 tok/s TG Prefill 560 · TTFT 40.628 ms | 10× | 2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 18 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 67,46 tok/s TG Prefill 568 · TTFT 39.939 ms | 10× | 2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 110 GB RAM | llama.cppgodclaw | Details → | |
| 19 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 60,89 tok/s TG Prefill 409 · TTFT 24.788 ms | 5× | 2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 20 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 55,85 tok/s TG Prefill 415 · TTFT 24.406 ms | 5× | 2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 110 GB RAM | llama.cppgodclaw | Details → | |
| 21 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 38,84 tok/s TG Prefill 258 · TTFT 10.963 ms | 1× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 126 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 22 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 36,99 tok/s TG Prefill 221 · TTFT 12.961 ms | 1× | 2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 23 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 35,58 tok/s TG Prefill 220 · TTFT 12.963 ms | 1× | 2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 110 GB RAM | llama.cppgodclaw | Details → | |
| 24 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 35,44 tok/s TG Prefill 249 · TTFT 90.371 ms | 10× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 31 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 25 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 32,77 tok/s TG Prefill 160 · TTFT 63.351 ms | 5× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 31 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 26 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 30,41 tok/s TG Prefill 713 · TTFT 3.416 ms | 1× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 27 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 25,97 tok/s TG Prefill 204 · TTFT 110.341 ms | 10× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_XL | Details → | |
| 28 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 22,67 tok/s TG Prefill 124 · TTFT 18.211 ms | 1× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 31 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 29 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 19,36 tok/s TG Prefill 158 · TTFT 64.302 ms | 5× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_XL | Details → | |
| 30 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,95 tok/s TG Prefill 94 · TTFT 24.951 ms | 1× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_XL | Details → |