Apple M3 Ultra 20P+8E+60GPU
GPU
96
GB
PERFORMANCE OVERVIEW
Model
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
445tokens/s
Generation Speed
34.4tokens/s
Time to First Token
2.67sec
LocalScore
179
COMPARE MODELS
1 models tested
Select Models
Qwen2.5 14B Instruct
Q4_K - Medium