Qwen/Qwen2.5 14B-Instruct

unknown·14B params·unknown
checkpoint: Qwen/Qwen2.5-14B-Instruct-AWQ
commit: 539535859b13
weights 9.29 GiB

All runs (5)

HardwareBackendShapeConc.Gen tok/sTTFTTPOT (ms)Out tokTotalVRAM Δ
GeForce RTX 3090 · 24 GiBvLLM 0.21.0 (cuda)chat1
42.6
59ms22.5741.60s0.000 GiB
GeForce RTX 3090 · 24 GiBvLLM 0.21.0 (cuda)agent1
40.6
56ms24.53558.73s0.000 GiB
GeForce RTX 3090 · 24 GiBvLLM 0.21.0 (cuda)codegen1
40.0
97ms24.962215.46s0.000 GiB
GeForce RTX 3090 · 24 GiBvLLM 0.21.0 (cuda)agent4
39.3
93ms25.23559.04s0.000 GiB
GeForce RTX 3090 · 24 GiBvLLM 0.21.0 (cuda)rag1
38.9
53ms24.5451.36s0.000 GiB

Environment

GeForce RTX 3090 · 24 GiB
cpuAMD EPYC 7302P 16-Core Processor
gpuNVIDIA GeForce RTX 3090
archNVIDIA
vram24 GiB (system 64.0 GiB)
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