🏆
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 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 661,81 tok/s TG Prefill 3.559 · TTFT 18.166 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 2 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 615,32 tok/s TG Prefill 5.005 · TTFT 17.982 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 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 614,42 tok/s TG Prefill 4.348 · TTFT 18.337 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 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 606,09 tok/s TG Prefill 3.754 · TTFT 19.156 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 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 530,93 tok/s TG Prefill 2.357 · TTFT 24.008 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 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 369,72 tok/s TG Prefill 3.178 · TTFT 6.224 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 7 | glm-4.7-flashZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 349,28 tok/s TG Prefill 7.891 · TTFT 3.899 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | openclaw_cliAWQ | Details → | |
| 8 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 339,73 tok/s TG Prefill 4.537 · TTFT 5.634 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 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 338,70 tok/s TG Prefill 4.134 · TTFT 5.849 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 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 327,67 tok/s TG Prefill 3.524 · TTFT 6.621 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 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 299,95 tok/s TG Prefill 2.073 · TTFT 8.616 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 → | |
| 12 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 276,46 tok/s TG Prefill 11.804 · TTFT 2.833 ms | 10× | 2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 13 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 269,51 tok/s TG Prefill 10.904 · TTFT 3.057 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 14 | glm-4.7-flashZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 233,82 tok/s TG Prefill 6.284 · TTFT 2.148 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | openclaw_cliAWQ | Details → | |
| 15 | glm-4.7-flashZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 211,45 tok/s TG Prefill 14.193 · TTFT 1.973 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | vLLMopenclaw_cliAWQ | Details → | |
| 16 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 197,32 tok/s TG Prefill 9.348 · TTFT 1.552 ms | 5× | 2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 17 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 188,12 tok/s TG Prefill 8.582 · TTFT 1.686 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 18 | glm-4.7-flashZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 151,70 tok/s TG Prefill 5.294 · TTFT 5.865 ms | 10× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 189 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 19 | glm-4.7-flashZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 144,63 tok/s TG Prefill 3.247 · TTFT 656 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | openclaw_cliAWQ | Details → | |
| 20 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 125,21 tok/s TG Prefill 2.615 · TTFT 815 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 21 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 114,95 tok/s TG Prefill 2.849 · TTFT 762 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 → | |
| 22 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 114,93 tok/s TG Prefill 3.570 · TTFT 601 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 → | |
| 23 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 107,89 tok/s TG Prefill 2.115 · TTFT 1.012 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 → | |
| 24 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 106,86 tok/s TG Prefill 3.108 · TTFT 689 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 → | |
| 25 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 104,08 tok/s TG Prefill 2.674 · TTFT 8.272 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 26 | glm-4.7-flashZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 103,06 tok/s TG Prefill 4.019 · TTFT 3.355 ms | 5× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 189 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 27 | glm-4.7-flashZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 102,50 tok/s TG Prefill 10.352 · TTFT 1.169 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | vLLMopenclaw_cliAWQ | Details → | |
| 28 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 99,46 tok/s TG Prefill 1.300 · TTFT 18.623 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 29 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 90,64 tok/s TG Prefill 3.471 · TTFT 630 ms | 1× | 2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 30 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 84,40 tok/s TG Prefill 3.192 · TTFT 679 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 31 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 83,92 tok/s TG Prefill 1.024 · TTFT 10.752 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 32 | glm-4.7-flashZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 48,92 tok/s TG Prefill 4.055 · TTFT 536 ms | 1× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | vLLMgodclawAWQ | Details → | |
| 33 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 44,21 tok/s TG Prefill 939 · TTFT 2.266 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 34 | glm-4.7-flashZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 43,51 tok/s TG Prefill 1.942 · TTFT 1.097 ms | 1× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 189 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 35 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 32,88 tok/s TG Prefill 982 · TTFT 3.379 ms | 1× | 3x AMD Radeon AI PRO R9700 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 36 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmark | 32,88 tok/s TG Prefill 982 · TTFT 3.379 ms | 1× | 3x AMD Radeon AI PRO R9700 i32x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawQ4_K_M | Details → | |
| 37 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 29,69 tok/s TG Prefill 223 · TTFT 109.515 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 38 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 24,65 tok/s TG Prefill 160 · TTFT 68.270 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 39 | glm-4.7-flashZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 21,28 tok/s TG Prefill 6.200 · TTFT 346 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | vLLMopenclaw_cliAWQ | Details → | |
| 40 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 20,78 tok/s TG Prefill 144 · TTFT 302.096 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 41 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 18,75 tok/s TG Prefill 987 · TTFT 26.527 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMgodclawFP8 | Details → | |
| 42 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 17,03 tok/s TG Prefill 104 · TTFT 105.008 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 43 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 15,67 tok/s TG Prefill 157 · TTFT 13.591 ms | 1× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 44 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 14,86 tok/s TG Prefill 133 · TTFT 150.792 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 45 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,20 tok/s TG Prefill 55 · TTFT 200.979 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 46 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 11,22 tok/s TG Prefill 103 · TTFT 20.742 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 47 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 10,94 tok/s TG Prefill 762 · TTFT 15.666 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMgodclawFP8 | Details → | |
| 48 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 9,87 tok/s TG Prefill 112 · TTFT 19.038 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 49 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 9,12 tok/s TG Prefill 94 · TTFT 251.044 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 50 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 9,08 tok/s TG Prefill 5.237 · TTFT 407 ms | 1× | 3x AMD Radeon AI PRO R9700 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 51 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmark | 9,08 tok/s TG Prefill 5.237 · TTFT 407 ms | 1× | 3x AMD Radeon AI PRO R9700 i32x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawAWQ | Details → | |
| 52 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 9,03 tok/s TG Prefill 138 · TTFT 172.301 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 53 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,50 tok/s TG Prefill 56 · TTFT 199.090 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 54 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,44 tok/s TG Prefill 51 · TTFT 41.695 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 55 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,44 tok/s TG Prefill 51 · TTFT 42.235 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 56 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,40 tok/s TG Prefill 51 · TTFT 41.828 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 57 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,27 tok/s TG Prefill 55 · TTFT 200.698 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 58 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,11 tok/s TG Prefill 133 · TTFT 16.005 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 59 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,01 tok/s TG Prefill 441 · TTFT 4.837 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMgodclawFP8 | Details → | |
| 60 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,20 tok/s TG Prefill 382 · TTFT 35.625 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 61 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,91 tok/s TG Prefill 73 · TTFT 29.342 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 62 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,34 tok/s TG Prefill 107 · TTFT 80.161 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 63 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,18 tok/s TG Prefill 10 · TTFT 226.444 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 64 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,55 tok/s TG Prefill 77 · TTFT 144.723 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 65 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,51 tok/s TG Prefill 83 · TTFT 25.669 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 66 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,34 tok/s TG Prefill 182 · TTFT 11.740 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 67 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,60 tok/s TG Prefill 108 · TTFT 79.520 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 68 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,13 tok/s TG Prefill 18 · TTFT 117.963 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 69 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,53 tok/s TG Prefill 78 · TTFT 109.360 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 70 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,19 tok/s TG Prefill 80 · TTFT 106.653 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 71 | glm-5.2-colibri744BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,03 tok/s TG Prefill 188 · TTFT 10.056 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition iAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 72 | glm-5.2-colibri744BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,03 tok/s TG Prefill 188 · TTFT 10.057 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | godclaw | Details → | |
| 73 | glm-5.2-colibri744BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,03 tok/s TG Prefill 188 · TTFT 10.045 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition iAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 74 | glm-5.2-colibri744BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,03 tok/s TG Prefill 188 · TTFT 10.056 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition iAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 75 | glm-5.2-colibri744BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,03 tok/s TG Prefill 174 · TTFT 10.848 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition iAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 76 | glm-5.2-colibri744BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,03 tok/s TG Prefill 185 · TTFT 10.186 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | godclaw | Details → | |
| 77 | glm-5.2-colibri744BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,03 tok/s TG Prefill 7 · TTFT 354.674 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition iAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | colibricolibriINT4 | Details → | |
| 78 | glm-5.2-colibri744BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,03 tok/s TG Prefill 211 · TTFT 10.088 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition iAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | colibricolibriINT4 | Details → | |
| 79 | glm-5.2-colibri744BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,03 tok/s TG Prefill 10 · TTFT 239.030 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition iAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | colibricolibri | Details → |

