Apple M3 Ultra 24P+8E+80GPU
GPU
512
GB
PERFORMANCE OVERVIEW
Model
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
579tokens/s
Generation Speed
35.9tokens/s
Time to First Token
2.03sec
LocalScore
217
COMPARE MODELS
1 models tested
Select Models
Qwen2.5 14B Instruct
Q4_K - Medium