NVIDIA GeForce RTX 3080 Laptop GPU
GPU
16
GB
PERFORMANCE OVERVIEW
Model
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
786tokens/s
Generation Speed
27.9tokens/s
Time to First Token
1.55sec
LocalScore
242
COMPARE MODELS
1 models tested
Select Models
Qwen2.5 14B Instruct
Q4_K - Medium