Ranglisten
LLM Leaderboard
Filtere reale Messergebnisse nach Benchmarktyp und Systemkonfiguration.
| # | Modell / Hersteller | Typ | Messwerte | Parallel | GPU / CPU / RAM | Runtime | Datum | ||
|---|---|---|---|---|---|---|---|---|---|
| 1 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba)Timebench 3 - Kombi (Prefill + Generation) | Performancebenchmark | 8,52 tok/s TG Prefill 71 · TTFT 152.830 ms | 5× | Keine GPU (CPU-only)51x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclaw Q4_K_M | 22.07.2026 | Details → | |
| 2 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba)Timebench 3 - Kombi (Prefill + Generation) | Performancebenchmark | 6,64 tok/s TG Prefill 73 · TTFT 33.548 ms | 1× | Keine GPU (CPU-only)51x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclaw Q4_K_M | 22.07.2026 | Details → | |
| 3 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba)Timebench 3 - Kombi (Prefill + Generation) | Performancebenchmark | 0,58 tok/s TG Prefill 77 · TTFT 216.585 ms | 10× | Keine GPU (CPU-only)51x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclaw Q4_K_M | 22.07.2026 | Details → |
