Apple M5 Max 6P+12E+40GPU
GPU
128
GB
PERFORMANCE OVERVIEW
Model
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
338tokens/s
Generation Speed
36.3tokens/s
Time to First Token
3.55sec
LocalScore
151
COMPARE MODELS
1 models tested
Select Models
Qwen2.5 14B Instruct
Q4_K - Medium