Qwen2.5 14B-Instruct
AWQ·14B params·safetensors
intelligence: see on Artificial Analysis →
checkpoint:
Qwen/Qwen2.5-14B-Instruct-AWQcommit:
539535859b13weights 9.29 GiB
All runs (15)
| Hardware | Backend | Mode | Shape | Conc. | Gen tok/s ↓ | Prefill tok/s | TTFT | TPOT (ms) | Prompt tok | Out tok | Total | VRAM Δ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-350w | codegen | 1 | 81.0 | 1765.7 | 44ms | 12.3 | 81 | 622 | 7.63s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-450w | codegen | 1 | 81.0 | 1763.5 | 44ms | 12.3 | 81 | 622 | 7.63s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-450w | chat | 1 | 80.7 | 1533.3 | 33ms | 12.1 | 49 | 74 | 908ms | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-350w | chat | 1 | 80.7 | 1509.8 | 34ms | 12.1 | 49 | 74 | 908ms | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-350w | agent | 1 | 80.1 | 21761.7 | 29ms | 12.4 | 606 | 355 | 4.41s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-450w | agent | 1 | 80.1 | 21655.7 | 29ms | 12.4 | 606 | 355 | 4.41s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-450w | rag | 1 | 76.3 | 30203.1 | 35ms | 12.3 | 855 | 45 | 675ms | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-350w | rag | 1 | 76.0 | 30227.2 | 36ms | 12.3 | 855 | 45 | 675ms | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-450w | agent | 4 | 74.2 | 10789.7 | 63ms | 13.4 | 606 | 355 | 4.77s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-350w | agent | 4 | 74.0 | 11489.7 | 65ms | 13.4 | 606 | 355 | 4.78s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB200 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline | chat | 1 | 42.6 | 859.6 | 59ms | 22.5 | 49 | 74 | 1.60s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB200 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline | agent | 1 | 40.6 | 10787.6 | 56ms | 24.5 | 606 | 355 | 8.73s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB200 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline | codegen | 1 | 40.0 | 803.9 | 97ms | 24.9 | 81 | 622 | 15.46s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB200 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline | agent | 4 | 39.3 | 7270.7 | 93ms | 25.2 | 606 | 355 | 9.04s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB200 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline | rag | 1 | 38.9 | 16420.1 | 53ms | 24.5 | 855 | 45 | 1.36s | 0.000 GiB |
Environment
GeForce RTX 3090 · 24 GiB
cpuAMD EPYC 7302P 16-Core Processor
gpuNVIDIA GeForce RTX 3090
archNVIDIA
vram24 GiB (system 64.0 GiB)
power420 W / 450 W max(93% cap)
backendvLLM 0.21.0 (cuda)
serverlemonade unknown
osUbuntu 24.04 LTS
kernel6.17.13-7-pve
driver590.48.01
python3.12.3
containerizedtrue
runs/cell5
warmups2
endpoint/v1/chat/completions
streamingtrue
GeForce RTX 3090 · 24 GiB
cpuAMD EPYC 7302P 16-Core Processor
gpuNVIDIA GeForce RTX 3090
archNVIDIA
vram24 GiB (system 64.0 GiB)
power200 W / 450 W max(44% cap)
backendvLLM 0.21.0 (cuda)
serverlemonade unknown
osUbuntu 24.04 LTS
kernel6.17.13-7-pve
driver590.48.01
python3.12.3
containerizedtrue
runs/cell5
warmups2
endpoint/v1/chat/completions
streamingtrue