🏆
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 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.560,53 tok/s TG Prefill 10.558 · TTFT 6.806 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclaw | Details → | |
| 2 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.505,61 tok/s TG Prefill 8.190 · TTFT 7.531 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cli | Details → | |
| 3 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.349,73 tok/s TG Prefill 11.193 · TTFT 7.579 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 4 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.309,27 tok/s TG Prefill 10.749 · TTFT 7.401 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 5 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.236,51 tok/s TG Prefill 7.739 · TTFT 8.840 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 6 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 883,39 tok/s TG Prefill 5.377 · TTFT 12.467 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 7 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 824,94 tok/s TG Prefill 9.828 · TTFT 2.187 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclaw | Details → | |
| 8 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 805,86 tok/s TG Prefill 7.558 · TTFT 2.503 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cli | Details → | |
| 9 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 786,22 tok/s TG Prefill 4.926 · TTFT 14.292 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocket | Details → | |
| 10 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 723,83 tok/s TG Prefill 9.782 · TTFT 2.438 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 11 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 720,85 tok/s TG Prefill 9.346 · TTFT 2.458 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 12 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 665,27 tok/s TG Prefill 6.912 · TTFT 2.829 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 13 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 487,60 tok/s TG Prefill 5.077 · TTFT 20.649 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 14 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 476,21 tok/s TG Prefill 5.858 · TTFT 20.719 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 15 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 474,97 tok/s TG Prefill 3.481 · TTFT 22.488 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 16 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 468,02 tok/s TG Prefill 4.949 · TTFT 4.084 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 17 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 430,04 tok/s TG Prefill 4.493 · TTFT 4.596 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocket | Details → | |
| 18 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 351,55 tok/s TG Prefill 1.164 · TTFT 38.427 ms | 10× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cli | Details → | |
| 19 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 333,12 tok/s TG Prefill 1.168 · TTFT 37.996 ms | 10× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cli | Details → | |
| 20 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 261,45 tok/s TG Prefill 4.824 · TTFT 6.145 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 21 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 255,30 tok/s TG Prefill 5.644 · TTFT 6.016 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 22 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 254,56 tok/s TG Prefill 3.174 · TTFT 7.205 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 23 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 235,12 tok/s TG Prefill 3.475 · TTFT 6.384 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 24 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 220,86 tok/s TG Prefill 4.538 · TTFT 425 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cli | Details → | |
| 25 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 217,11 tok/s TG Prefill 6.786 · TTFT 284 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclaw | Details → | |
| 26 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 204,77 tok/s TG Prefill 5.075 · TTFT 381 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 27 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 204,69 tok/s TG Prefill 5.251 · TTFT 367 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 28 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 198,63 tok/s TG Prefill 993 · TTFT 14.781 ms | 5× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cli | Details → | |
| 29 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 198,55 tok/s TG Prefill 1.000 · TTFT 14.742 ms | 5× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cli | Details → | |
| 30 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 197,21 tok/s TG Prefill 3.720 · TTFT 518 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 31 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 133,84 tok/s TG Prefill 3.838 · TTFT 503 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocket | Details → | |
| 32 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 132,34 tok/s TG Prefill 2.522 · TTFT 3.929 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 33 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 129,00 tok/s TG Prefill 3.247 · TTFT 594 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 34 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 108,03 tok/s TG Prefill 2.184 · TTFT 10.407 ms | 10× | 2x NVIDIA GeForce RTX 2060Intel(R) Core(TM) i5-7400 CPU @ 3.00GHz · 7 GB RAM | llama.cppopenclaw_cli | Details → | |
| 35 | Ornith-1.0-9B9BQ8_0DeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 97,31 tok/s TG Prefill 2.232 · TTFT 10.125 ms | 10× | 2x NVIDIA GeForce RTX 2060Intel(R) Core(TM) i5-7400 CPU @ 3.00GHz · 7 GB RAM | llama.cppopenclaw_cli | Details → | |
| 36 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 80,74 tok/s TG Prefill 1.579 · TTFT 6.372 ms | 5× | 2x NVIDIA GeForce RTX 2060Intel(R) Core(TM) i5-7400 CPU @ 3.00GHz · 7 GB RAM | llama.cppopenclaw_cli | Details → | |
| 37 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 78,93 tok/s TG Prefill 1.889 · TTFT 1.021 ms | 1× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 38 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 77,28 tok/s TG Prefill 2.856 · TTFT 676 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 39 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 76,74 tok/s TG Prefill 3.638 · TTFT 530 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 40 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 75,38 tok/s TG Prefill 3.900 · TTFT 494 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 41 | Ornith-1.0-9B9BQ8_0DeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 73,89 tok/s TG Prefill 1.619 · TTFT 6.216 ms | 5× | 2x NVIDIA GeForce RTX 2060Intel(R) Core(TM) i5-7400 CPU @ 3.00GHz · 7 GB RAM | llama.cppopenclaw_cli | Details → | |
| 42 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 70,84 tok/s TG Prefill 920 · TTFT 2.098 ms | 1× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cli | Details → | |
| 43 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 64,46 tok/s TG Prefill 592 · TTFT 16.869 ms | 5× | NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | llama.cppopenclaw_cli | Details → | |
| 44 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 42,36 tok/s TG Prefill 986 · TTFT 1.973 ms | 1× | 2x NVIDIA GeForce RTX 2060Intel(R) Core(TM) i5-7400 CPU @ 3.00GHz · 7 GB RAM | llama.cppopenclaw_cli | Details → | |
| 45 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 37,65 tok/s TG Prefill 776 · TTFT 29.085 ms | 10× | NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | llama.cppopenclaw_cli | Details → | |
| 46 | Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 33,54 tok/s TG Prefill 547 · TTFT 3.535 ms | 1× | NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | llama.cppopenclaw_cli | Details → | |
| 47 | Ornith-1.0-9B9BQ8_0DeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 29,62 tok/s TG Prefill 1.037 · TTFT 1.873 ms | 1× | 2x NVIDIA GeForce RTX 2060Intel(R) Core(TM) i5-7400 CPU @ 3.00GHz · 7 GB RAM | llama.cppopenclaw_cli | Details → |