Apple M4 4P+6E+8GPU
GPU
16
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
895tokens/s
61tokens/s
Generation Speed
65.8tokens/s
7.2tokens/s
Time to First Token
1.44sec
20.48sec
LocalScore
344
28
COMPARE MODELS
2 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium