Accelerator icon
NVIDIA A40-48Q
GPU
48
GB
PERFORMANCE OVERVIEW
Model
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
1707tokens/s
Generation Speed
39.5tokens/s
Time to First Token
762ms
LocalScore
446
COMPARE MODELS

1 models tested

Select Models

Qwen2.5 14B Instruct

Q4_K - Medium

NVIDIA A40-48Q - 48GB