NVIDIA
Nemotron-3-Super-120B-A12B120B
Benchmark profile and published results.
MoE120B
Position in the field
Best values compared
Best metrics of this model against the minimum, average and maximum of all published systems.
Generation600,9 tok/s
Min 0,0Ø 518,2Max 2.414,4
Ueber dem Durchschnitt · 244 Systeme im Feld
Prefill2.709 tok/s
Min 7Ø 6.972Max 39.029
Unter dem Durchschnitt · 244 Systeme im Feld
Time to First Token1.129 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
CPUby processor
AMD Ryzen 9 9950X 16-Core Processor 600,9 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 423,4 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 80,5 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 32,6 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 18,9 tok/sNVIDIA Grace 11,4 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 5,5 tok/s
Throughput & latency
Performance benchmark
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 600,88 tok/s TG Prefill 2.709 · TTFT 21.268 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-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 423,38 tok/s TG Prefill 2.668 · TTFT 27.534 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 3 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 423,31 tok/s TG Prefill 2.911 · TTFT 27.041 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 4 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 423,26 tok/s TG Prefill 2.897 · TTFT 27.048 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 5 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 422,61 tok/s TG Prefill 2.701 · TTFT 27.527 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 6 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 348,02 tok/s TG Prefill 2.385 · TTFT 7.651 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-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 238,46 tok/s TG Prefill 2.760 · TTFT 8.787 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 8 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 238,33 tok/s TG Prefill 2.465 · TTFT 9.171 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 9 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 237,98 tok/s TG Prefill 2.469 · TTFT 9.177 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 10 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 236,07 tok/s TG Prefill 2.719 · TTFT 8.878 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 11 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 129,00 tok/s TG Prefill 1.909 · TTFT 1.129 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 12 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 87,17 tok/s TG Prefill 1.587 · TTFT 1.411 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 13 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 87,06 tok/s TG Prefill 1.359 · TTFT 1.804 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 14 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 86,77 tok/s TG Prefill 1.759 · TTFT 1.226 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 15 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 86,68 tok/s TG Prefill 1.767 · TTFT 1.224 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 16 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 80,54 tok/s TG Prefill 1.417 · TTFT 3.615 ms | 10× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cli batched-bench ROCmQ4_K_M | Details → | |
| 17 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 69,35 tok/s TG Prefill 1.423 · TTFT 1.799 ms | 5× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cli batched-bench ROCmQ4_K_M | Details → | |
| 18 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 34,26 tok/s TG Prefill 1.009 · TTFT 2.135 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 19 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 33,55 tok/s TG Prefill 853 · TTFT 600 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cli batched-bench ROCmQ4_K_M | Details → | |
| 20 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 32,59 tok/s TG Prefill 122 · TTFT 237.566 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 21 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 29,79 tok/s TG Prefill 109 · TTFT 133.175 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 22 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 29,17 tok/s TG Prefill 851 · TTFT 2.528 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 23 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,86 tok/s TG Prefill 805 · TTFT 2.387 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 24 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,15 tok/s TG Prefill 74 · TTFT 191.503 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 25 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,04 tok/s TG Prefill 74 · TTFT 191.933 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 26 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 22,99 tok/s TG Prefill 74 · TTFT 191.470 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 27 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 22,28 tok/s TG Prefill 85 · TTFT 331.062 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 28 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 22,26 tok/s TG Prefill 85 · TTFT 330.872 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 29 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 21,82 tok/s TG Prefill 85 · TTFT 331.365 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 30 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 20,17 tok/s TG Prefill 211 · TTFT 47.089 ms | 5× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 31 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 18,86 tok/s TG Prefill 117 · TTFT 322.251 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 32 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 16,81 tok/s TG Prefill 67 · TTFT 215.255 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 33 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 16,07 tok/s TG Prefill 104 · TTFT 170.078 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 34 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 15,60 tok/s TG Prefill 71 · TTFT 293.317 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 35 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 14,79 tok/s TG Prefill 187 · TTFT 10.300 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 36 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,19 tok/s TG Prefill 96 · TTFT 191.977 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 37 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,14 tok/s TG Prefill 93 · TTFT 194.178 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 38 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,12 tok/s TG Prefill 98 · TTFT 21.966 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 39 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 11,39 tok/s TG Prefill 1.495 · TTFT 1.449 ms | 1× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | vLLMgodclawNVFP4 | Details → | |
| 40 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 9,96 tok/s TG Prefill 61 · TTFT 35.263 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 41 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 9,93 tok/s TG Prefill 61 · TTFT 35.078 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 42 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 9,93 tok/s TG Prefill 58 · TTFT 37.175 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 43 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,36 tok/s TG Prefill 90 · TTFT 96.800 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 44 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,90 tok/s TG Prefill 88 · TTFT 98.810 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 45 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,87 tok/s TG Prefill 61 · TTFT 35.354 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 46 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,67 tok/s TG Prefill 99 · TTFT 21.860 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 47 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,54 tok/s TG Prefill 62 · TTFT 139.871 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 48 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,41 tok/s TG Prefill 62 · TTFT 140.359 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 49 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,07 tok/s TG Prefill 78 · TTFT 27.484 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 50 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,91 tok/s TG Prefill 82 · TTFT 26.277 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 51 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,66 tok/s TG Prefill 62 · TTFT 34.936 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 52 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,48 tok/s TG Prefill 42 · TTFT 207.107 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ8_0 | Details → | |
| 53 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,42 tok/s TG Prefill 41 · TTFT 212.358 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ8_0 | Details → | |
| 54 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,25 tok/s TG Prefill 37 · TTFT 57.803 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ8_0 | Details → | |
| 55 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,16 tok/s TG Prefill 42 · TTFT 207.388 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ8_0 | Details → | |
| 56 | Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,93 tok/s TG Prefill 42 · TTFT 206.643 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ8_0 | Details → |
Agent & chat rating
Harness benchmark
Noch keine Harnessbenchmarks fuer dieses Modell.