Apple M2 Ultra 16P+8E+76GPU
GPU
192
GB
PERFORMANCE OVERVIEW
Model
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
469tokens/s
Generation Speed
36.5tokens/s
Time to First Token
2.49sec
LocalScore
190
COMPARE MODELS
1 models tested
Select Models
Qwen2.5 14B Instruct
Q4_K - Medium