🏆
Rankings
LLM Leaderboard
Real measurements of every tested language model on real, named hardware – rated by raw speed (performance in tokens per second, prefill and time to first token) and by practical task quality in complete agent and chat runs (harness). Pick a benchmark type below or filter by model, maker and hardware to see exactly what is tested and how the results are produced.
⚡ Performance (tok/s)🤖 Harness quality👥 Concurrency🖥️ real hardware
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 203,47 tok/s TG Prefill 963 · TTFT 58.166 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 → | |
| 2 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 200,61 tok/s TG Prefill 1.005 · TTFT 54.811 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 → | |
| 3 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 197,19 tok/s TG Prefill 552 · TTFT 68.166 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 4 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 174,90 tok/s TG Prefill 848 · TTFT 34.870 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 5 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 167,22 tok/s TG Prefill 896 · TTFT 65.273 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-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 127,55 tok/s TG Prefill 986 · TTFT 17.763 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-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 120,39 tok/s TG Prefill 573 · TTFT 26.333 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 8 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 118,40 tok/s TG Prefill 1.007 · TTFT 19.503 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-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 113,48 tok/s TG Prefill 978 · TTFT 18.052 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-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 99,03 tok/s TG Prefill 811 · TTFT 23.516 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-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,14 tok/s TG Prefill 506 · TTFT 123.878 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 12 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 87,25 tok/s TG Prefill 547 · TTFT 119.494 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 13 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 51,74 tok/s TG Prefill 518 · TTFT 40.780 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 14 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 50,46 tok/s TG Prefill 539 · TTFT 37.888 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 15 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 50,46 tok/s TG Prefill 517 · TTFT 4.146 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 16 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,30 tok/s TG Prefill 979 · TTFT 2.203 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 17 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,23 tok/s TG Prefill 756 · TTFT 2.908 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 → | |
| 18 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,82 tok/s TG Prefill 750 · TTFT 2.935 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 → | |
| 19 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 44,51 tok/s TG Prefill 942 · TTFT 2.274 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 → | |
| 20 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 41,15 tok/s TG Prefill 809 · TTFT 2.652 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 → | |
| 21 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 38,08 tok/s TG Prefill 288 · TTFT 117.541 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 22 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 38,05 tok/s TG Prefill 280 · TTFT 122.770 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 23 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 32,44 tok/s TG Prefill 172 · TTFT 124.920 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 24 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 28,50 tok/s TG Prefill 313 · TTFT 43.987 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 25 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 28,09 tok/s TG Prefill 148 · TTFT 146.240 ms | 10× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 26 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 25,49 tok/s TG Prefill 163 · TTFT 118.721 ms | 10× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 27 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 25,42 tok/s TG Prefill 178 · TTFT 109.132 ms | 10× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 28 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 25,04 tok/s TG Prefill 233 · TTFT 54.589 ms | 5× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 29 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,92 tok/s TG Prefill 304 · TTFT 38.888 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 30 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,85 tok/s TG Prefill 298 · TTFT 32.384 ms | 5× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 31 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,08 tok/s TG Prefill 299 · TTFT 39.857 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 32 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 22,58 tok/s TG Prefill 284 · TTFT 34.055 ms | 5× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 33 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 21,60 tok/s TG Prefill 535 · TTFT 4.022 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 34 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 21,58 tok/s TG Prefill 531 · TTFT 4.053 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 35 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 20,39 tok/s TG Prefill 172 · TTFT 265.241 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 36 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 18,49 tok/s TG Prefill 521 · TTFT 4.134 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 37 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 16,87 tok/s TG Prefill 213 · TTFT 278.913 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 38 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 16,57 tok/s TG Prefill 383 · TTFT 5.006 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 39 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 16,47 tok/s TG Prefill 394 · TTFT 5.441 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 40 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 15,96 tok/s TG Prefill 401 · TTFT 4.771 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 41 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 15,57 tok/s TG Prefill 412 · TTFT 4.643 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 42 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 14,39 tok/s TG Prefill 171 · TTFT 124.363 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 43 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 13,25 tok/s TG Prefill 547 · TTFT 3.937 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 44 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 13,25 tok/s TG Prefill 548 · TTFT 3.936 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 45 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,02 tok/s TG Prefill 219 · TTFT 125.268 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 46 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 10,66 tok/s TG Prefill 160 · TTFT 61.556 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 47 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,96 tok/s TG Prefill 338 · TTFT 6.286 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 48 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,98 tok/s TG Prefill 159 · TTFT 12.016 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 49 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,47 tok/s TG Prefill 29 · TTFT 302.685 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 50 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,37 tok/s TG Prefill 28 · TTFT 305.613 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 51 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,37 tok/s TG Prefill 28 · TTFT 303.667 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 52 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,33 tok/s TG Prefill 28 · TTFT 304.593 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 53 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,28 tok/s TG Prefill 29 · TTFT 303.468 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 54 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,24 tok/s TG Prefill 28 · TTFT 306.669 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 55 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,69 tok/s TG Prefill 161 · TTFT 13.385 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 56 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,69 tok/s TG Prefill 212 · TTFT 10.143 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 57 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,21 tok/s TG Prefill 26 · TTFT 83.718 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 58 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,21 tok/s TG Prefill 26 · TTFT 83.997 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 59 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,21 tok/s TG Prefill 26 · TTFT 83.458 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → |
