🏆
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 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 364,13 tok/s TG Prefill 15.658 · TTFT 1.918 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 2 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 358,15 tok/s TG Prefill 19.410 · TTFT 1.565 ms | 10× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 3 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 355,86 tok/s TG Prefill 24.866 · TTFT 2.634 ms | 10× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | vLLMgodclaw | Details → | |
| 4 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 333,18 tok/s TG Prefill 17.060 · TTFT 1.879 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 → | |
| 5 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 289,42 tok/s TG Prefill 10.849 · TTFT 1.212 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 6 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 259,86 tok/s TG Prefill 9.253 · TTFT 3.361 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 → | |
| 7 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 253,98 tok/s TG Prefill 19.902 · TTFT 780 ms | 5× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | vLLMgodclaw | Details → | |
| 8 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 225,82 tok/s TG Prefill 9.739 · TTFT 3.277 ms | 10× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 9 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 213,88 tok/s TG Prefill 16.055 · TTFT 898 ms | 5× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 10 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 207,49 tok/s TG Prefill 12.047 · TTFT 1.151 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 → | |
| 11 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 187,50 tok/s TG Prefill 6.698 · TTFT 2.090 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 → | |
| 12 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 168,19 tok/s TG Prefill 7.879 · TTFT 1.850 ms | 5× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 13 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 108,65 tok/s TG Prefill 5.041 · TTFT 551 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 → | |
| 14 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 106,40 tok/s TG Prefill 3.776 · TTFT 651 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 → | |
| 15 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 104,76 tok/s TG Prefill 6.603 · TTFT 399 ms | 1× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 16 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 93,07 tok/s TG Prefill 7.599 · TTFT 324 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 17 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 73,93 tok/s TG Prefill 4.119 · TTFT 596 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 18 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 52,34 tok/s TG Prefill 7.155 · TTFT 346 ms | 1× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | vLLMgodclaw | Details → | |
| 19 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,47 tok/s TG Prefill 33 · TTFT 369.084 ms | 5× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 20 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,22 tok/s TG Prefill 24 · TTFT 103.262 ms | 1× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 21 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,07 tok/s TG Prefill 33 · TTFT 360.019 ms | 10× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → |