Qwen (Alibaba)
Qwen2.5-7B-Instruct7B
Benchmark profile and published results.
Dense7B
Position in the field
Best values compared
Best metrics of this model against the minimum, average and maximum of all published systems.
Generation442,0 tok/s
Min 0,1Ø 161,0Max 717,6
Ueber dem Durchschnitt · 338 Systeme im Feld
Prefill16.333 tok/s
Min 39Ø 5.997Max 52.503
Ueber dem Durchschnitt · 338 Systeme im Feld
Time to First Token411 ms
Min 156Ø 18.924Max 354.928
Ueber dem Durchschnitt · 338 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
Throughput & latency
Performance benchmark
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 442,02 tok/s TG Prefill 16.333 · TTFT 3.286 ms | 10× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | vLLMgodclaw | Details → | |
| 2 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 326,73 tok/s TG Prefill 13.426 · TTFT 1.202 ms | 5× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | vLLMgodclaw | Details → | |
| 3 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 261,39 tok/s TG Prefill 10.101 · TTFT 2.985 ms | 10× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 4 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 250,57 tok/s TG Prefill 9.085 · TTFT 3.442 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 5 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 178,27 tok/s TG Prefill 8.322 · TTFT 1.724 ms | 5× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 6 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 168,09 tok/s TG Prefill 6.490 · TTFT 2.083 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 7 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 160,26 tok/s TG Prefill 4.979 · TTFT 6.510 ms | 10× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 8 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 108,79 tok/s TG Prefill 3.816 · TTFT 3.796 ms | 5× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 9 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 76,83 tok/s TG Prefill 3.292 · TTFT 785 ms | 1× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 10 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 68,23 tok/s TG Prefill 5.975 · TTFT 411 ms | 1× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | vLLMgodclaw | Details → | |
| 11 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 58,79 tok/s TG Prefill 4.166 · TTFT 593 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 12 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 56,92 tok/s TG Prefill 2.151 · TTFT 1.142 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 → |
Agent & chat rating
Harness benchmark
Noch keine Harnessbenchmarks fuer dieses Modell.
