Apple M2 Ultra 16P+8E+76GPU
GPU
128
GB
PERFORMANCE OVERVIEW
Model
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
471tokens/s
Generation Speed
36.6tokens/s
Time to First Token
2.48sec
LocalScore
191
COMPARE MODELS
1 models tested
Select Models
Qwen2.5 14B Instruct
Q4_K - Medium