🏆
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 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 561,43 tok/s TG Prefill 27.407 · TTFT 973 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 2 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 503,33 tok/s TG Prefill 112.346 · TTFT 242 ms | 10× | NVIDIA GeForce RTX 4090AMD Ryzen 3 3100 4-Core Processor · 61 GB RAM | vLLMopenclaw_cliFP8 | Details → | |
| 3 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 495,51 tok/s TG Prefill 19.609 · TTFT 628 ms | 5× | AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 4 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 480,52 tok/s TG Prefill 22.887 · TTFT 1.208 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 5 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 449,35 tok/s TG Prefill 21.718 · TTFT 571 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 6 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 384,19 tok/s TG Prefill 49.306 · TTFT 1.939 ms | 10× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | vLLMgodclaw | Details → | |
| 7 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 302,60 tok/s TG Prefill 4.126 · TTFT 3.252 ms | 5× | AMD Oberon (PlayStation 5)AMD Zen2 8-Core (PlayStation 5) · 16 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 8 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 281,62 tok/s TG Prefill 14.942 · TTFT 839 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 9 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 260,24 tok/s TG Prefill 38.946 · TTFT 372 ms | 5× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | vLLMgodclaw | Details → | |
| 10 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 258,23 tok/s TG Prefill 81.661 · TTFT 159 ms | 5× | NVIDIA GeForce RTX 4090AMD Ryzen 3 3100 4-Core Processor · 61 GB RAM | vLLMopenclaw_cliFP8 | Details → | |
| 11 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 252,73 tok/s TG Prefill 1.840 · TTFT 1.356 ms | 1× | AMD Oberon (PlayStation 5)AMD Zen2 8-Core (PlayStation 5) · 16 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 12 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 243,73 tok/s TG Prefill 13.492 · TTFT 181 ms | 1× | AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 13 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 227,38 tok/s TG Prefill 13.749 · TTFT 177 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 14 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 143,39 tok/s TG Prefill 7.110 · TTFT 411 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 15 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 54,53 tok/s TG Prefill 14.803 · TTFT 166 ms | 1× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | vLLMgodclaw | Details → | |
| 16 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 52,80 tok/s TG Prefill 20.717 · TTFT 121 ms | 1× | NVIDIA GeForce RTX 4090AMD Ryzen 3 3100 4-Core Processor · 61 GB RAM | vLLMopenclaw_cliFP8 | Details → | |
| 17 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,04 tok/s TG Prefill 108 · TTFT 227.805 ms | 10× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 18 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,43 tok/s TG Prefill 83 · TTFT 139.346 ms | 5× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 19 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,80 tok/s TG Prefill 23 · TTFT 106.805 ms | 1× | Keine GPU (CPU-only)AMD Jaguar 8-Core (PlayStation 4) · 5 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 20 | Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,17 tok/s TG Prefill 80 · TTFT 30.662 ms | 1× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → |