Qwen2.5-Coder 32B-Instruct
AWQ·32B params·safetensors
intelligence: see on Artificial Analysis →
checkpoint:
Qwen/Qwen2.5-Coder-32B-Instruct-AWQcommit:
1ed0a6145da0weights 18.00 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 | 41.3 | 815.9 | 96ms | 24.1 | 81 | 720 | 17.46s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-450w | codegen | 1 | 41.3 | 817.0 | 96ms | 24.1 | 81 | 720 | 17.46s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-450w | agent | 1 | 41.2 | 11391.4 | 53ms | 24.2 | 606 | 295 | 7.56s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-350w | agent | 1 | 41.1 | 11373.2 | 53ms | 24.2 | 606 | 295 | 7.56s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-450w | chat | 1 | 41.0 | 839.5 | 61ms | 23.8 | 49 | 100 | 2.39s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-350w | chat | 1 | 41.0 | 878.1 | 58ms | 23.8 | 49 | 100 | 2.39s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-350w | rag | 1 | 40.1 | 16203.0 | 53ms | 24.0 | 855 | 62 | 1.77s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-450w | rag | 1 | 40.0 | 16188.0 | 53ms | 24.0 | 855 | 62 | 1.77s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-350w | agent | 4 | 38.8 | 7704.1 | 99ms | 25.7 | 606 | 295 | 7.61s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB420 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline-pl-450w | agent | 4 | 38.7 | 8186.8 | 100ms | 25.7 | 606 | 295 | 7.62s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB200 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline | chat | 1 | 19.5 | 452.6 | 112ms | 49.9 | 49 | 100 | 4.76s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB200 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline | codegen | 1 | 19.3 | 417.2 | 187ms | 51.4 | 81 | 720 | 37.27s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB200 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline | agent | 1 | 19.2 | 5080.7 | 119ms | 51.6 | 606 | 363 | 18.90s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB200 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline | rag | 1 | 18.9 | 8013.5 | 111ms | 52.2 | 855 | 62 | 3.73s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB200 Wdrv 590 | vLLM 0.21.0 (cuda) | baseline | agent | 4 | 18.8 | 3535.8 | 175ms | 52.6 | 606 | 295 | 15.71s | 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