Apple M4 Pro 8P+4E+16GPU
GPU
64
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
1859tokens/s
151tokens/s
Generation Speed
112tokens/s
16.1tokens/s
Time to First Token
670ms
8.46sec
LocalScore
677
66
COMPARE MODELS
2 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium