Qwen (Alibaba)
Qwen3-14B14B
Benchmark profile and published results.
Dense14B
Position in the field
Best values compared
Best metrics of this model against the minimum, average and maximum of all published systems.
Generation280,8 tok/s
Min 0,0Ø 245,7Max 3.484,3
Ueber dem Durchschnitt · 4971 Systeme im Feld
Prefill8.760 tok/s
Min 4Ø 4.892Max 112.346
Ueber dem Durchschnitt · 4953 Systeme im Feld
Time to First Token748 ms
Min 20Ø 31.420Max 535.235
Ueber dem Durchschnitt · 4968 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 | Qwen3-14B14BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 280,80 tok/s TG Prefill 8.760 · TTFT 5.247 ms | 10× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | vLLMgodclaw | Details → | |
| 2 | Qwen3-14B14BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 198,18 tok/s TG Prefill 7.101 · TTFT 2.296 ms | 5× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | vLLMgodclaw | Details → | |
| 3 | Qwen3-14B14BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 189,57 tok/s TG Prefill 4.215 · TTFT 6.476 ms | 10× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 4 | Qwen3-14B14BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 186,94 tok/s TG Prefill 4.086 · TTFT 6.892 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 | Qwen3-14B14BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 113,91 tok/s TG Prefill 2.991 · TTFT 4.155 ms | 5× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 6 | Qwen3-14B14BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 107,74 tok/s TG Prefill 2.967 · TTFT 4.204 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 → | |
| 7 | Qwen3-14B14BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,73 tok/s TG Prefill 2.063 · TTFT 1.206 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 → | |
| 8 | Qwen3-14B14BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,29 tok/s TG Prefill 2.015 · TTFT 1.225 ms | 1× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 9 | Qwen3-14B14BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 44,22 tok/s TG Prefill 3.257 · TTFT 748 ms | 1× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | vLLMgodclaw | Details → | |
| 10 | Qwen3-14B14BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 15,53 tok/s TG Prefill 525 · TTFT 4.974 ms | 1× | Keine GPU (CPU-only)Apple M6 (unified CPU/GPU SoC, ARM64, AdvSIMD) · 24 GB RAM | lmstudio-mlxlmstudioMLX 4bit | Details → | |
| 11 | Qwen3-14B14BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 14,03 tok/s TG Prefill 321 · TTFT 8.097 ms | 1× | Keine GPU (CPU-only)Apple M6 (unified CPU/GPU SoC) · 24 GB RAM | Ollamaopenclaw_cliQ4_K_M | Details → | |
| 12 | Qwen3-14B14BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 10,58 tok/s TG Prefill 185 · TTFT 13.217 ms | 1× | AMD Oberon (PlayStation 5)AMD Zen2 8-Core (PlayStation 5) · 16 GB RAM | llama.cppgodclawQ4_K_M | Details → |
Agent & chat rating
Harness benchmark
Noch keine Harnessbenchmarks fuer dieses Modell.

