Qwen/Qwen2.5 7B-Instruct

unknown·7B params·unknown
checkpoint: Qwen/Qwen2.5-7B-Instruct-AWQ
commit: b25037543e93
weights 5.19 GiB

All runs (5)

HardwareBackendShapeConc.Gen tok/sTTFTTPOT (ms)Out tokTotalVRAM Δ
GeForce RTX 3090 · 24 GiBvLLM 0.21.0 (cuda)chat1
85.2
35ms11.4991.14s0.000 GiB
GeForce RTX 3090 · 24 GiBvLLM 0.21.0 (cuda)rag1
77.9
32ms12.053780ms0.000 GiB
GeForce RTX 3090 · 24 GiBvLLM 0.21.0 (cuda)agent1
77.0
31ms13.03955.10s0.000 GiB
GeForce RTX 3090 · 24 GiBvLLM 0.21.0 (cuda)codegen1
77.0
55ms12.96999.03s0.000 GiB
GeForce RTX 3090 · 24 GiBvLLM 0.21.0 (cuda)agent4
75.7
58ms13.03955.22s0.000 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