Qwen (Alibaba)
Qwen2.5-32B-Instruct-AWQ32B
Benchmark profile and published results.
Dense32B
Position in the field
Best values compared
Best metrics of this model against the minimum, average and maximum of all published systems.
Generation510,3 tok/s
Min 0,0Ø 248,3Max 2.491,2
Ueber dem Durchschnitt · 3969 Systeme im Feld
Prefill7.178 tok/s
Min 4Ø 4.741Max 55.260
Ueber dem Durchschnitt · 3969 Systeme im Feld
Time to First Token681 ms
Min 20Ø 33.962Max 535.235
Ueber dem Durchschnitt · 3967 Systeme im Feld
Harness-Quote13,4 %
Min 10,0Ø 54,4Max 90,6
Unter dem Durchschnitt · 30 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 510,3 tok/sNVIDIA GeForce RTX 5090 473,9 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 412,6 tok/sNVIDIA RTX A6000 362,6 tok/sNVIDIA GeForce RTX 3090 Ti 223,8 tok/sAMD Radeon PRO W7900 Dual Slot 89,6 tok/sAMD Radeon PRO W7800 48GB 69,9 tok/sNVIDIA GeForce RTX 5070 Ti 45,0 tok/sAMD Radeon AI PRO R9700 22,3 tok/s
CPUby processor
AMD Ryzen 9 9950X 16-Core Processor 510,3 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 473,9 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 412,6 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 362,6 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 223,8 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 89,6 tok/s
Throughput & latency
Performance benchmark
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 510,34 tok/s TG Prefill 6.104 · TTFT 4.473 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 2 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 473,96 tok/s TG Prefill 5.347 · TTFT 21.026 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 3 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 473,90 tok/s TG Prefill 5.066 · TTFT 22.401 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 4 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 412,58 tok/s TG Prefill 6.480 · TTFT 24.413 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 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 406,23 tok/s TG Prefill 5.348 · TTFT 25.223 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 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 362,62 tok/s TG Prefill 7.178 · TTFT 5.398 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 7 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 343,00 tok/s TG Prefill 3.698 · TTFT 31.024 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 → | |
| 8 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 332,07 tok/s TG Prefill 6.084 · TTFT 5.812 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 9 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 300,61 tok/s TG Prefill 4.931 · TTFT 2.537 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 10 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 253,96 tok/s TG Prefill 5.304 · TTFT 6.596 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 11 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 250,73 tok/s TG Prefill 5.071 · TTFT 5.931 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 12 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 230,34 tok/s TG Prefill 5.542 · TTFT 3.017 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 13 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 223,82 tok/s TG Prefill 2.436 · TTFT 44.343 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 14 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 222,01 tok/s TG Prefill 2.436 · TTFT 45.755 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketAWQ | Details → | |
| 15 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 219,09 tok/s TG Prefill 6.838 · TTFT 6.933 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 → | |
| 16 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 213,98 tok/s TG Prefill 5.838 · TTFT 7.294 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 → | |
| 17 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 213,52 tok/s TG Prefill 5.123 · TTFT 3.257 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 18 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 191,84 tok/s TG Prefill 3.437 · TTFT 9.776 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliAWQ | Details → | |
| 19 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 181,11 tok/s TG Prefill 3.409 · TTFT 8.759 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 → | |
| 20 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 127,64 tok/s TG Prefill 2.262 · TTFT 14.457 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 21 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 124,33 tok/s TG Prefill 2.267 · TTFT 13.440 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketAWQ | Details → | |
| 22 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 121,67 tok/s TG Prefill 2.552 · TTFT 5.654 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliAWQ | Details → | |
| 23 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 89,55 tok/s TG Prefill 1.146 · TTFT 25.938 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 24 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 71,16 tok/s TG Prefill 2.321 · TTFT 1.217 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 25 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 69,89 tok/s TG Prefill 2.286 · TTFT 17.114 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 26 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 69,22 tok/s TG Prefill 3.226 · TTFT 762 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 27 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 68,44 tok/s TG Prefill 3.289 · TTFT 747 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 28 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 64,51 tok/s TG Prefill 3.434 · TTFT 718 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 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 63,99 tok/s TG Prefill 3.625 · TTFT 681 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 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 58,57 tok/s TG Prefill 2.697 · TTFT 914 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 31 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 54,82 tok/s TG Prefill 2.450 · TTFT 1.003 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 32 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,90 tok/s TG Prefill 1.182 · TTFT 12.306 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 33 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 44,95 tok/s TG Prefill 698 · TTFT 216.065 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 34 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 40,26 tok/s TG Prefill 1.449 · TTFT 1.698 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 35 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 40,21 tok/s TG Prefill 2.441 · TTFT 1.008 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 → | |
| 36 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 40,18 tok/s TG Prefill 1.444 · TTFT 1.705 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketAWQ | Details → | |
| 37 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 37,93 tok/s TG Prefill 1.679 · TTFT 9.606 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 38 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 30,24 tok/s TG Prefill 1.503 · TTFT 1.640 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliAWQ | Details → | |
| 39 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,62 tok/s TG Prefill 710 · TTFT 3.465 ms | 1× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 40 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 25,69 tok/s TG Prefill 709 · TTFT 63.754 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 41 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 22,29 tok/s TG Prefill 857 · TTFT 2.683 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 42 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 9,14 tok/s TG Prefill 52 · TTFT 231.639 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 43 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,59 tok/s TG Prefill 50 · TTFT 190.219 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 44 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,56 tok/s TG Prefill 51 · TTFT 189.942 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 45 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,52 tok/s TG Prefill 50 · TTFT 190.485 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 46 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,42 tok/s TG Prefill 50 · TTFT 190.404 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 47 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,41 tok/s TG Prefill 449 · TTFT 5.486 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 48 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,34 tok/s TG Prefill 50 · TTFT 190.236 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 49 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,29 tok/s TG Prefill 858 · TTFT 2.871 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 50 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,43 tok/s TG Prefill 37 · TTFT 66.123 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 51 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,42 tok/s TG Prefill 37 · TTFT 66.102 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 52 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,42 tok/s TG Prefill 37 · TTFT 66.094 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → |
Agent & chat rating
Harness benchmark
| # | Model / Maker | Metrics | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|
| 1 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Harness benchmarkTool Usage V 1.0 | 235 Pkt 13,4% · 15/15 Aufg. · 1.783,0 s | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | openclaw_cli | Details → | |
| 2 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Harness benchmarkTool Usage Standard 1.0 | 298 Pkt 10,0% · 16/16 Aufg. · 4.687,0 s | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 123 GB RAM | openclaw_cli | Details → |