Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
🏆
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
Reset
Messwert:
#Modell / HerstellerMesswerteParallelGPU / CPU / RAMRuntime
1gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.022,79 tok/s TG
Prefill 18.744 · TTFT 2.204 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclaw
2gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
616,01 tok/s TG
Prefill 13.778 · TTFT 803 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclaw
3gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
144,58 tok/s TG
Prefill 7.078 · TTFT 281 ms
1×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclaw
4gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
106,26 tok/s TG
Prefill 3.145 · TTFT 6.467 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
5gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
102,29 tok/s TG
Prefill 3.255 · TTFT 6.446 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_0
6gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
90,20 tok/s TG
Prefill 3.429 · TTFT 5.889 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
7gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
90,13 tok/s TG
Prefill 3.332 · TTFT 6.049 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
8gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
80,95 tok/s TG
Prefill 2.992 · TTFT 8.497 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
9gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
79,73 tok/s TG
Prefill 778 · TTFT 12.722 ms
5×AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAMllama.cppgodclawUD-Q4_K_M
10gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
79,32 tok/s TG
Prefill 763 · TTFT 12.964 ms
5×AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAMllama.cppgodclawQ4_0
11gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
78,87 tok/s TG
Prefill 774 · TTFT 12.771 ms
5×AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAMllama.cppgodclawUD-Q4_K_M
12gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
78,01 tok/s TG
Prefill 753 · TTFT 13.128 ms
5×AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAMllama.cppgodclawQ4_0
13gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
77,67 tok/s TG
Prefill 881 · TTFT 23.171 ms
10×AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAMllama.cppgodclawQ4_0
14gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
76,77 tok/s TG
Prefill 886 · TTFT 23.041 ms
10×AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAMllama.cppgodclawUD-Q4_K_M
15gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
76,77 tok/s TG
Prefill 853 · TTFT 23.960 ms
10×AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAMllama.cppgodclawUD-Q4_K_M
16gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
75,25 tok/s TG
Prefill 878 · TTFT 23.266 ms
10×AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAMllama.cppgodclawQ4_0
17gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
59,13 tok/s TG
Prefill 2.833 · TTFT 3.492 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
18gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
59,12 tok/s TG
Prefill 2.866 · TTFT 3.452 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_0
19gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
58,64 tok/s TG
Prefill 2.917 · TTFT 3.395 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
20gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
56,64 tok/s TG
Prefill 3.217 · TTFT 6.338 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_0
21gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
55,17 tok/s TG
Prefill 3.161 · TTFT 6.427 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_0
22gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
55,07 tok/s TG
Prefill 3.075 · TTFT 6.594 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_0
23gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
45,96 tok/s TG
Prefill 2.789 · TTFT 3.550 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_0
24gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
40,73 tok/s TG
Prefill 2.786 · TTFT 3.598 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_0
25gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
39,82 tok/s TG
Prefill 2.513 · TTFT 4.069 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
26gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
32,76 tok/s TG
Prefill 781 · TTFT 2.535 ms
1×AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAMllama.cppgodclawQ4_0
27gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
32,62 tok/s TG
Prefill 731 · TTFT 2.700 ms
1×AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAMllama.cppgodclawUD-Q4_K_M
28gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
32,38 tok/s TG
Prefill 757 · TTFT 2.611 ms
1×AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAMllama.cppgodclawQ4_0
29gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
32,36 tok/s TG
Prefill 763 · TTFT 2.591 ms
1×AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAMllama.cppgodclawUD-Q4_K_M
30gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
32,22 tok/s TG
Prefill 2.641 · TTFT 3.757 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
31gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
22,25 tok/s TG
Prefill 2.529 · TTFT 3.924 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_0
32gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
12,35 tok/s TG
Prefill 1.938 · TTFT 1.019 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
33gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
12,35 tok/s TG
Prefill 1.961 · TTFT 1.008 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
34gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
12,34 tok/s TG
Prefill 1.960 · TTFT 1.007 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
35gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
12,33 tok/s TG
Prefill 1.971 · TTFT 1.002 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_0
36gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
12,33 tok/s TG
Prefill 1.960 · TTFT 1.008 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_0
37gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
12,33 tok/s TG
Prefill 1.950 · TTFT 1.012 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_0
38gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
12,33 tok/s TG
Prefill 1.951 · TTFT 1.012 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
39gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
11,60 tok/s TG
Prefill 1.763 · TTFT 1.142 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_0