Apple M2 4P+4E+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
330tokens/s
60tokens/s
Generation Speed
17.8tokens/s
7.0tokens/s
Time to First Token
4.28sec
21.43sec
LocalScore
111
27
COMPARE MODELS
2 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium