NVIDIA GeForce RTX 4090
GPU
22
GB
PERFORMANCE OVERVIEW
Model
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
3056tokens/s
Generation Speed
31.6tokens/s
Time to First Token
485ms
LocalScore
594
COMPARE MODELS
1 models tested
Select Models
Qwen2.5 14B Instruct
Q4_K - Medium