Apple M1 Ultra 16P+4E+64GPU
GPU
128
GB
PERFORMANCE OVERVIEW
Model
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
377tokens/s
Generation Speed
33.3tokens/s
Time to First Token
3.10sec
LocalScore
159
COMPARE MODELS
1 models tested
Select Models
Qwen2.5 14B Instruct
Q4_K - Medium