NVIDIA
Nemotron-3-Nano-30B-A3B30B
Benchmark profile and published results.
MoE30B
Position in the field
Best values compared
Best metrics of this model against the minimum, average and maximum of all published systems.
Generation1.773,5 tok/s
Min 0,0Ø 518,2Max 2.414,4
Ueber dem Durchschnitt · 244 Systeme im Feld
Prefill16.604 tok/s
Min 7Ø 6.972Max 39.029
Ueber dem Durchschnitt · 244 Systeme im Feld
Time to First Token396 ms
Min 114Ø 27.182Max 354.674
Ueber dem Durchschnitt · 244 Systeme im Feld
Performance profile
Throughput by hardware & engine
Each bubble is a GPU, CPU or engine – position shows prompt processing (X) and output speed (Y), bubble size the number of runs.
GPUby graphics card
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.773,5 tok/sNVIDIA GeForce RTX 5090 1.722,1 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.654,6 tok/sNVIDIA GeForce RTX 3090 Ti 897,5 tok/sNVIDIA RTX A6000 756,7 tok/sNVIDIA GeForce RTX 5070 Ti 263,3 tok/sAMD Radeon AI PRO R9700 217,4 tok/sNVIDIA GB10 58,3 tok/sNVIDIA GeForce RTX 2060 6,6 tok/s
CPUby processor
AMD Ryzen 9 9950X 16-Core Processor 1.773,5 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 1.722,1 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.654,6 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 897,5 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 756,7 tok/sAMD Ryzen 5 5600X 6-Core Processor 404,7 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 263,3 tok/sNVIDIA Grace 58,3 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 6,6 tok/s
Throughput & latency
Performance benchmark
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.773,53 tok/s TG Prefill 8.720 · TTFT 6.861 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 2 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.722,05 tok/s TG Prefill 7.387 · TTFT 7.500 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 3 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.654,57 tok/s TG Prefill 10.472 · TTFT 7.000 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 4 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.554,37 tok/s TG Prefill 10.928 · TTFT 6.920 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 5 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.540,50 tok/s TG Prefill 7.349 · TTFT 8.077 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 6 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.007,80 tok/s TG Prefill 7.787 · TTFT 2.444 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 7 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 990,65 tok/s TG Prefill 6.523 · TTFT 2.724 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 8 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 930,89 tok/s TG Prefill 9.176 · TTFT 2.377 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 9 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 929,05 tok/s TG Prefill 10.212 · TTFT 2.281 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 10 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 899,02 tok/s TG Prefill 6.589 · TTFT 2.842 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 11 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 897,46 tok/s TG Prefill 4.457 · TTFT 13.871 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 12 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 756,69 tok/s TG Prefill 7.030 · TTFT 14.551 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 13 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 755,10 tok/s TG Prefill 6.964 · TTFT 14.586 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 14 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 588,46 tok/s TG Prefill 20.028 · TTFT 1.512 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliAWQ | Details → | |
| 15 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 550,00 tok/s TG Prefill 3.904 · TTFT 4.878 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 16 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 533,54 tok/s TG Prefill 16.604 · TTFT 5.626 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawBF16 | Details → | |
| 17 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 450,85 tok/s TG Prefill 6.453 · TTFT 4.464 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 18 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 448,68 tok/s TG Prefill 6.418 · TTFT 4.484 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 19 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 419,41 tok/s TG Prefill 14.676 · TTFT 885 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliAWQ | Details → | |
| 20 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 404,72 tok/s TG Prefill 4.793 · TTFT 5.226 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | llamacppIQ4_NL | Details → | |
| 21 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 403,66 tok/s TG Prefill 6.688 · TTFT 9.919 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 22 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 403,64 tok/s TG Prefill 6.778 · TTFT 9.874 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 23 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 397,81 tok/s TG Prefill 11.797 · TTFT 1.550 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawBF16 | Details → | |
| 24 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 361,45 tok/s TG Prefill 21.222 · TTFT 1.462 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliFP8 | Details → | |
| 25 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 359,35 tok/s TG Prefill 3.984 · TTFT 549 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 26 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 356,96 tok/s TG Prefill 5.493 · TTFT 396 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 27 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 330,76 tok/s TG Prefill 5.147 · TTFT 418 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 28 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 330,02 tok/s TG Prefill 6.337 · TTFT 339 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 29 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 326,60 tok/s TG Prefill 6.610 · TTFT 326 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 30 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 300,10 tok/s TG Prefill 3.941 · TTFT 2.860 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | llamacppIQ4_NL | Details → | |
| 31 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 263,34 tok/s TG Prefill 784 · TTFT 55.800 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 32 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 259,38 tok/s TG Prefill 5.806 · TTFT 3.790 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 33 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 254,44 tok/s TG Prefill 15.556 · TTFT 831 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliFP8 | Details → | |
| 34 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 228,62 tok/s TG Prefill 4.731 · TTFT 2.273 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 35 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 221,98 tok/s TG Prefill 3.364 · TTFT 641 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 36 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 218,20 tok/s TG Prefill 6.296 · TTFT 1.720 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 37 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 217,41 tok/s TG Prefill 2.159 · TTFT 4.552 ms | 5× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 38 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 216,68 tok/s TG Prefill 6.212 · TTFT 1.740 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 39 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 212,92 tok/s TG Prefill 3.795 · TTFT 6.753 ms | 10× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 40 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 207,55 tok/s TG Prefill 3.338 · TTFT 3.388 ms | 5× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 41 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 203,05 tok/s TG Prefill 5.938 · TTFT 3.711 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 42 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 196,02 tok/s TG Prefill 3.211 · TTFT 670 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | llamacppIQ4_NL | Details → | |
| 43 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 192,66 tok/s TG Prefill 2.706 · TTFT 3.642 ms | 5× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 44 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 192,16 tok/s TG Prefill 2.755 · TTFT 3.564 ms | 5× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 45 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 191,04 tok/s TG Prefill 5.708 · TTFT 732 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawBF16 | Details → | |
| 46 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 187,06 tok/s TG Prefill 2.824 · TTFT 3.499 ms | 5× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 47 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 181,01 tok/s TG Prefill 3.865 · TTFT 5.849 ms | 10× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 48 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 180,63 tok/s TG Prefill 5.766 · TTFT 396 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliAWQ | Details → | |
| 49 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 178,15 tok/s TG Prefill 3.106 · TTFT 7.058 ms | 10× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 50 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 176,89 tok/s TG Prefill 5.267 · TTFT 2.069 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 51 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 174,14 tok/s TG Prefill 4.417 · TTFT 488 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 52 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 174,04 tok/s TG Prefill 4.376 · TTFT 492 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 53 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 167,21 tok/s TG Prefill 3.497 · TTFT 6.460 ms | 10× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 54 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 163,13 tok/s TG Prefill 683 · TTFT 22.415 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 55 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 159,67 tok/s TG Prefill 4.269 · TTFT 504 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 56 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 154,95 tok/s TG Prefill 3.643 · TTFT 6.292 ms | 10× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 57 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 153,33 tok/s TG Prefill 23.508 · TTFT 1.417 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawBF16 | Details → | |
| 58 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 145,62 tok/s TG Prefill 4.471 · TTFT 482 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 59 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 145,08 tok/s TG Prefill 4.478 · TTFT 481 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 60 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 131,91 tok/s TG Prefill 4.351 · TTFT 495 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 61 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 125,69 tok/s TG Prefill 1.771 · TTFT 1.085 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 62 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 121,93 tok/s TG Prefill 270 · TTFT 141.290 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 63 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 121,92 tok/s TG Prefill 269 · TTFT 140.690 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 64 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 121,82 tok/s TG Prefill 269 · TTFT 141.070 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 65 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 118,53 tok/s TG Prefill 5.670 · TTFT 398 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliFP8 | Details → | |
| 66 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 106,46 tok/s TG Prefill 2.518 · TTFT 762 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 67 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 105,88 tok/s TG Prefill 2.728 · TTFT 789 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 68 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 103,21 tok/s TG Prefill 2.393 · TTFT 803 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 69 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 102,46 tok/s TG Prefill 10.458 · TTFT 1.708 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawBF16 | Details → | |
| 70 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 99,92 tok/s TG Prefill 2.124 · TTFT 903 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 71 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 78,25 tok/s TG Prefill 2.525 · TTFT 867 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 72 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 75,86 tok/s TG Prefill 219 · TTFT 62.421 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 73 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 75,47 tok/s TG Prefill 218 · TTFT 62.596 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 74 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 74,58 tok/s TG Prefill 217 · TTFT 63.094 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 75 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 68,05 tok/s TG Prefill 598 · TTFT 3.605 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 76 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 58,25 tok/s TG Prefill 5.466 · TTFT 395 ms | 1× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | vLLMgodclawNVFP4 | Details → | |
| 77 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 38,30 tok/s TG Prefill 5.839 · TTFT 376 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawBF16 | Details → | |
| 78 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 32,16 tok/s TG Prefill 180 · TTFT 11.985 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 79 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 32,01 tok/s TG Prefill 179 · TTFT 12.037 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 80 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 31,32 tok/s TG Prefill 178 · TTFT 12.130 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 81 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,60 tok/s TG Prefill 73 · TTFT 150.849 ms | 5× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 82 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,88 tok/s TG Prefill 61 · TTFT 35.422 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 83 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,27 tok/s TG Prefill 81 · TTFT 206.882 ms | 10× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → |
Agent & chat rating
Harness benchmark
Noch keine Harnessbenchmarks fuer dieses Modell.
