🏆 Rangliste
Highscore
Die besten Läufe im direkten Ranking – umschaltbar zwischen Performance (Token/s) und Harness (Aufgabenpunkte).
| # | Modell / Hersteller | Grafikkarte | CPU / RAM | Generation | Prefill | TG | TTFT | Parallel | Runtime | |
|---|---|---|---|---|---|---|---|---|---|---|
| 🥇 | gemma-4-E2B-it5BGoogle | NVIDIA GeForce RTX 5090 | AMD Ryzen 7 5800X3D 8-Core Processor 126 GB | 2.491,2 tok/s |
15.814 | 2.491,2 | 4382 ms | 10× | llama.cppcodex_cliQ4_K_M | Details → |
| 🥈 | gemma-4-E2B-it5BGoogle | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 2.414,4 tok/s |
20.277 | 2.414,4 | 4106 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 🥉 | Nemotron-3-Nano-4B4BNVIDIA | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 2.182,7 tok/s |
10.599 | 2.182,7 | 5597 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 4 | gemma-4-E2B-it5BGoogle | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 2.143,6 tok/s |
13.632 | 2.143,6 | 4819 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 5 | gpt-oss-20b20BOpenAI | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 1.995,4 tok/s |
16.158 | 1.995,4 | 5309 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 6 | gpt-oss-20b20BOpenAI | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 1.993,5 tok/s |
16.318 | 1.993,5 | 5322 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 7 | Nemotron-3-Nano-4B4BNVIDIA | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 1.937,7 tok/s |
9.452 | 1.937,7 | 6287 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 8 | Nemotron-3-Nano-4B4BNVIDIA | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 1.911,6 tok/s |
10.116 | 1.911,6 | 6244 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 9 | Nemotron-3-Nano-4B4BNVIDIA | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 1.897,0 tok/s |
10.984 | 1.897,0 | 6226 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 10 | gpt-oss-20b20BOpenAI | NVIDIA GeForce RTX 5090 | AMD Ryzen 7 5800X3D 8-Core Processor 126 GB | 1.890,7 tok/s |
14.771 | 1.890,7 | 5489 ms | 10× | llama.cppcodex_cliQ4_K_M | Details → |
| 11 | Nemotron-3-Nano-4B4BNVIDIA | NVIDIA GeForce RTX 5090 | AMD Ryzen 7 5800X3D 8-Core Processor 126 GB | 1.878,7 tok/s |
7.717 | 1.878,7 | 6689 ms | 10× | llama.cppcodex_cliQ4_K_M | Details → |
| 12 | gpt-oss-20b20BOpenAI | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 1.835,7 tok/s |
15.972 | 1.835,7 | 5760 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 13 | Nemotron-3-Nano-4B4BNVIDIA | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 1.830,3 tok/s |
9.399 | 1.830,3 | 6598 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 14 | gpt-oss-20b20BOpenAI | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 1.819,5 tok/s |
19.732 | 1.819,5 | 5578 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 15 | gpt-oss-20b20BOpenAI | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 1.802,0 tok/s |
18.226 | 1.802,0 | 5604 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 16 | Ornith-1.0-35B35BDeepReinforce | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 1.799,4 tok/s |
9.192 | 1.799,4 | 8876 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 17 | Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 1.791,5 tok/s |
7.972 | 1.791,5 | 6996 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 18 | Nemotron-3-Nano-30B-A3B30BNVIDIA | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 1.773,5 tok/s |
8.720 | 1.773,5 | 6861 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 19 | Nemotron-Cascade-2-30B-A3B30BNVIDIA | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 1.768,1 tok/s |
8.360 | 1.768,1 | 6952 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 20 | Laguna-XS-2.1Poolside | NVIDIA GeForce RTX 5090 | AMD Ryzen 7 5800X3D 8-Core Processor 126 GB | 1.765,0 tok/s |
8.542 | 1.765,0 | 7776 ms | 10× | llama.cppcodex_cliQ4_K_M | Details → |
| 21 | gemma-4-E4B-it8BGoogle | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 1.758,6 tok/s |
13.889 | 1.758,6 | 5964 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 22 | Laguna-XS-2.1Poolside | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 1.757,4 tok/s |
9.025 | 1.757,4 | 7343 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 23 | Laguna-XS-2.1Poolside | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 1.753,8 tok/s |
9.267 | 1.753,8 | 7328 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 24 | gemma-4-E2B-it5BGoogle | NVIDIA GeForce RTX 5070 Ti | AMD Ryzen Threadripper PRO 5975WX 32-Cores 247 GB | 1.744,0 tok/s |
13.641 | 1.744,0 | 5790 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 25 | gemma-4-E2B-it5BGoogle | NVIDIA GeForce RTX 5070 Ti | AMD Ryzen Threadripper PRO 5975WX 32-Cores 247 GB | 1.743,1 tok/s |
12.148 | 1.743,1 | 5881 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 26 | gpt-oss-20b20BOpenAI | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 1.742,1 tok/s |
12.852 | 1.742,1 | 6156 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 27 | Laguna-XS-2.1Poolside | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 1.740,4 tok/s |
9.653 | 1.740,4 | 7257 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 28 | Laguna-XS-2.1Poolside | NVIDIA GeForce RTX 5090 | AMD Ryzen 7 5800X3D 8-Core Processor 126 GB | 1.740,1 tok/s |
8.571 | 1.740,1 | 7785 ms | 10× | llama.cppcodex_cliQ4_K_M | Details → |
| 29 | Laguna-XS-2.1Poolside | NVIDIA GeForce RTX 5090 | AMD Ryzen 7 5800X3D 8-Core Processor 126 GB | 1.738,4 tok/s |
8.872 | 1.738,4 | 7721 ms | 10× | llama.cppcodex_cliQ4_K_M | Details → |
| 30 | Nemotron-3-Nano-30B-A3B30BNVIDIA | NVIDIA GeForce RTX 5090 | AMD Ryzen 7 5800X3D 8-Core Processor 126 GB | 1.722,1 tok/s |
7.387 | 1.722,1 | 7499 ms | 10× | llama.cppcodex_cliQ4_K_M | Details → |
| 31 | Nemotron-Cascade-2-30B-A3B30BNVIDIA | NVIDIA GeForce RTX 5090 | AMD Ryzen 7 5800X3D 8-Core Processor 126 GB | 1.719,2 tok/s |
8.044 | 1.719,2 | 7375 ms | 10× | llama.cppcodex_cliQ4_K_M | Details → |
| 32 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) | NVIDIA GeForce RTX 5090 | AMD Ryzen 7 5800X3D 8-Core Processor 126 GB | 1.716,6 tok/s |
12.604 | 1.716,6 | 6861 ms | 10× | llama.cppcodex_cliQ4_K_M | Details → |
| 33 | Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA | NVIDIA GeForce RTX 5090 | AMD Ryzen 7 5800X3D 8-Core Processor 126 GB | 1.706,7 tok/s |
7.511 | 1.706,7 | 7506 ms | 10× | llama.cppcodex_cliQ4_K_M | Details → |
| 34 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 1.690,0 tok/s |
14.458 | 1.690,0 | 6608 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 35 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) | NVIDIA GeForce RTX 5090 | AMD Ryzen 7 5800X3D 8-Core Processor 126 GB | 1.683,8 tok/s |
10.169 | 1.683,8 | 7361 ms | 10× | llama.cppcodex_cliQ4_K_M | Details → |
| 36 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) | NVIDIA GeForce RTX 5090 | AMD Ryzen 7 5800X3D 8-Core Processor 126 GB | 1.673,6 tok/s |
9.186 | 1.673,6 | 7566 ms | 10× | llama.cppcodex_cliQ4_K_M | Details → |
| 37 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) | NVIDIA GeForce RTX 5090 | AMD Ryzen 7 5800X3D 8-Core Processor 126 GB | 1.671,0 tok/s |
11.920 | 1.671,0 | 7068 ms | 10× | llama.cppcodex_cliQ4_K_M | Details → |
| 38 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 1.670,5 tok/s |
10.926 | 1.670,5 | 7140 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 39 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 1.658,1 tok/s |
13.451 | 1.658,1 | 6808 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 40 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) | NVIDIA GeForce RTX 5090 | AMD Ryzen 7 5800X3D 8-Core Processor 126 GB | 1.655,9 tok/s |
10.520 | 1.655,9 | 7268 ms | 10× | llama.cppcodex_cliQ4_K_M | Details → |
| 41 | Nemotron-Cascade-2-30B-A3B30BNVIDIA | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 1.655,2 tok/s |
10.591 | 1.655,2 | 7004 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 42 | Nemotron-3-Nano-30B-A3B30BNVIDIA | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 1.654,6 tok/s |
10.472 | 1.654,6 | 6999 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 43 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 1.653,3 tok/s |
10.581 | 1.653,3 | 7258 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 44 | Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 1.651,0 tok/s |
11.364 | 1.651,0 | 6871 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 45 | Nemotron-Cascade-2-30B-A3B30BNVIDIA | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 1.650,7 tok/s |
11.398 | 1.650,7 | 6886 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 46 | Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 1.649,9 tok/s |
10.323 | 1.649,9 | 7065 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 47 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 1.639,0 tok/s |
13.790 | 1.639,0 | 6892 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 48 | Laguna-XS-2.1Poolside | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 1.629,9 tok/s |
11.384 | 1.629,9 | 7322 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
| 49 | North-Mini-Code-1.0Cohere | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | AMD Ryzen 9 9950X 16-Core Processor 92 GB | 1.621,0 tok/s |
8.046 | 1.621,0 | 7550 ms | 10× | llama.cppgodclawUD-Q4_K_M | Details → |
| 50 | Laguna-XS-2.1Poolside | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | AMD Ryzen Threadripper PRO 9965WX 24-Cores 125 GB | 1.620,5 tok/s |
10.729 | 1.620,5 | 7428 ms | 10× | llama.cppgodclawQ4_K_M | Details → |
Ranking aus veröffentlichten Benchmarks. Sortiert nach Generation-Durchsatz. Wie wird gemessen?
